Vision Transformer

Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image classification, which primarily focuses on what. One possible reason is that classification-oriented backbones tend to emphasize semantic information about what, while implicitly entangling or suppressing information about where. In this work, we focus on an inductive bias termed what-where separation, which encourages models to represent object appearance and spatial location in a decomposed manner. To incorporate this bias throughout an attentive backbone in the style of Vision Transformer (ViT), we propose the What-Where Transformer (WWT). Our method introduces two key novel designs: (1) it treats tokens as representations of what and attention maps as representations of where, and processes them in concurrent feed-forward modules via a multi-stream, slot-based architecture; (2) it reuses both the final-layer tokens and attention maps for downstream tasks, and directly exposes them to gradients derived from task losses, thereby facilitating more effective and explicit learning of localization. We demonstrate that even under standard single-label classification-based supervision on ImageNet, WWT exhibits emergent multiple object discovery directly from raw attention maps, rather than via additional postprocessing such as token clustering. Furthermore, WWT achieves superior performance compared to ViT-based methods on zero-shot object discovery and weakly supervised semantic segmentation, and it is transferable to various localization setups with minimal modifications. Code will be published after acceptance.

Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Transformer interpretation. From the perspective of attention and gradient, we conduct an in-depth study of Transformer interpretation and propose a method to achieve it by guiding the gradient direction, or more precisely, the attention direction. The method enables more comprehensive interpretation of feature regions, offers detail interpretation, and helps to better understand Transformer mechanism. Leveraging the difference in how Vision Transformer (ViT) and humans perceive images, we alter the class of an image in a way that is almost imperceptible to the human eye. This class rewriting phenomenon may potentially pose security risks in certain scenarios.

We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without large-scale pretraining. Keeping the architecture and optimization procedure fixed, we compare a Baseline protocol with a Modern protocol (AutoAugment/ColorJitter, CutMix, and Label Smoothing) on CIFAR-10, CIFAR-100, and Tiny-ImageNet, characterizing each attention head via Mean Attention Distance (MAD) and normalized entropy. Across all three datasets, the Modern protocol produces more local and more concentrated attention in early layers; on CIFAR-100, the minimum MAD drops from 0.316 (Baseline) to 0.008 (Modern). To identify the source of this effect, we conduct an ablation study on CIFAR-100 by adding or removing each component individually. The results identify CutMix as the determining component within our experiments: all conditions with CutMix exhibit MAD 0.024, while all conditions without CutMix remain at MAD 0.210. AutoAugment and Label Smoothing show no independent effect on locality. Taken together, these findings suggest that the pressure to classify from partial image regions, induced by CutMix, can promote the emergence of local attention in Vision Transformers.

Vision Transformers (ViTs) implement depth by stacking independently parameterized blocks, but it remains unclear how much of this parameterization is necessary and how much can be replaced by recurrent reuse. We study this question with bViT, a single-block recurrent ViT that repeatedly applies the same transformer block while preserving the iterative computation of a deep model. On ImageNet-1K, bViT-B reaches 0.779 validation accuracy compared with 0.789 for ViT-B under the same training recipe and computational budget, while using 8.6M rather than 86.6M parameters. This correspondence becomes stronger with model width, while narrow recurrent models exhibit a substantial performance gap. Beyond classification, the single-block formulation provides a controlled testbed for studying how transformer computation evolves with depth, since the same heads, neurons, and weight matrices can be tracked across recurrent steps. Analyses of attention, activation patterns, and step-conditioned spectral pruning reveal temporally organized behavior and step-dependent utilization of the shared parameters. bViT also transfers competitively to downstream tasks while enabling highly parameter-efficient adaptation. Our work shows that much of the performance associated with independently parameterized ViT depth can be recovered through recurrent reuse of a single sufficiently wide transformer block.

Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep learning approaches have achieved promising results on static scenes, two critical limitations remain unaddressed: existing architectures fail to exploit temporal coherence across frames, leaving dynamic ghost imaging largely unsolved, and they assume additive Gaussian noise models that do not reflect the true Poissonian statistics of real single-photon hardware. We present DynGhost (Dynamic Ghost Imaging Transformer), a transformer architecture that addresses both limitations through alternating spatial and temporal attention blocks. Our quantum-aware training framework, based on physically accurate detector simulations (SNSPDs, SPADs, SiPMs) and Anscombe variance-stabilizing normalization, resolves the distribution shift that causes classical models to fail under realistic hardware constraints. Experiments across multiple benchmarks demonstrate that DynGhost outperforms both traditional reconstruction methods and existing deep learning architectures, with particular gains in dynamic and photon-starved settings.

Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VENμS show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution.

Multi-modal medical imaging enables comprehensive diagnostics, yet current foundation models process 2D (e.g. X-ray) and 3D (e.g. CT) data with separate, dimensionality-specific architectures. We present MultiMedVision, a unified framework for joint 2D/3D representation learning built on a Sparse Vision Transformer. Our model uses 3D Rotary Positional Embeddings and variable-length sequence packing to process mixed-modality batches natively within a shared latent space, without modality-specific adapters or treating 3D volumes as 2D slice sequences. Trained with a self-supervised objective on chest X-rays (MIMIC-CXR) and CT scans (CT-RATE), and using a single shared encoder with 5x less data, MultiMedVision achieves competitive performance on both 2D benchmarks (Macro AUROC 0.82 on MIMIC, 0.84 on CheXpert) and 3D tasks (0.85 on CT-RATE). Analysis of the learned representations reveals coexisting modality-specific and shared feature subspaces, demonstrating that unified cross-dimensional representation learning is feasible without sacrificing modality-specific performance.

Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether these observations coincide: does ViT depth implement approximately autonomous linear dynamics, admitting a single operator $K$ applied recurrently across a contiguous span? We test this using Dynamic Mode Decomposition (DMD), which fits $K$ from selected, consecutive hidden-state pairs and predicts $p$ steps ahead via $K^p$. On four pretrained DINO ViTs, we study the regularization, rank, and calibration budget required for stable fitting. For short spans ($p \leq 4$), $K^p$ tracks an unconstrained endpoint map to within $0.02$ cosine similarity on DINOv3-H/16+, while also recovering intermediate activations at each skipped block. At early cut starts, the fitted operators compress to rank $\ll d$ with minimal calibration data, and across tokens, cls is most amenable to linearization; both properties decay monotonically with depth. Yet this local fidelity does not transfer downstream. At the final hidden state, after propagating through the remaining blocks, an identity baseline becomes competitive.

Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise stochastic exposure to quantization noise and reveals depth-precision trade-offs. Building on APQ, we propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimizes exit thresholds and bit-widths under explicit risk control to improve inference stability. MAQEE establishes a superior Pareto frontier in the accuracy-efficiency trade-off, reducing BOPs by up to 95% while maintaining accuracy and outperforming strong baselines by up to 20% across classification, detection, and segmentation tasks.

Transformer architecture search (TAS) discovers optimal vision transformer (ViT) architectures automatically, reducing human effort to manually design ViTs. However, existing TAS methods suffer from the feature collapse problem, where subnets within a supernet fail to learn subnet-specific features, mainly due to the shared weights in a supernet, limiting the performance of individual subnets. To address this, we propose TAS-LoRA, a novel method that introduces parameter-efficient low-rank adaptation (LoRA) to enable subnet-specific feature learning, while maintaining computational efficiency. TAS-LoRA incorporates a Mixture-of-LoRAExperts (MoLE) strategy, where a lightweight router dynamically assigns LoRA experts based on subnet architectures, and introduces a group-wise router initialization technique to encourage diverse feature learning across experts early in training. Extensive experiments on ImageNet and several transfer learning benchmarks, including CIFAR-10/100, Flowers, CARS, and INAT-19, demonstrate that TAS-LoRA mitigates feature collapse effectively, improving performance over state-of-the-art TAS methods significantly.

A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard student ViT, is sufficient to recover the full benefit of the teacher's pre-trained weights. We revisit this finding on a comprehensive benchmark of 20 teachers from 11 well-known ViT families and reveal that Attention Transfer is not universally effective. While 7 families transfer successfully, 4 consistently fail, falling up to 5.1% below the from-scratch no-transfer baseline. Further results demonstrate that this failure is family-consistent across model sizes, and persists under extended training durations, different transfer datasets, and out-of-distribution evaluations. Controlled analyses then consistently localize the problem to the attention-routing channel, indicating that the key issue is not whether the student can match the teacher's attention patterns, but whether the matched patterns remain functional for the student. Crucially, we identify architectural mismatch between the pre-trained teacher and the standard student as the primary mechanism. By adding only the teacher's native architectural components to the student in a randomly initialized state, we completely reverse the failure for all 4 families. Notably, these components alone do not improve from-scratch training, confirming that they specifically unlock the usability of the teacher's attention. We further show that this failure is not explained by the inadequate choice of transfer loss, differences in pre-training recipes, or the intrinsic quality of attention maps. Our findings refine the prevailing understanding of attention in ViT representations: attention is sufficient only when the student architecture matches the teacher.

Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness changes, providing high dynamic range and high temporal resolution. However, existing event-based trackers often neglect the intrinsic spatial sparsity and temporal density of event data, while relying on a single fixed temporal-window sampling strategy that is suboptimal under varying motion dynamics. In this paper, we propose an event sparsity-aware tracking framework that explicitly models event-density variations across multiple temporal scales. Specifically, the proposed framework progressively injects sparse, medium-density, and dense event search regions into a three-stage Vision Transformer backbone, enabling hierarchical multi-density feature learning. Furthermore, we introduce a sparsity-aware Mixture-of-Experts module to encourage expert specialization under different sparsity patterns, and design a dynamic pondering strategy to adaptively adjust the inference depth according to tracking difficulty. Extensive experiments on FE240hz, COESOT, and EventVOT demonstrate that the proposed approach achieves a favorable trade-off between tracking accuracy and computational efficiency. The source code will be released on https://github.com/Event-AHU/OpenEvTracking.

Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep learning, this also serves to improve by-design interpretability, often by using part-centric attention mechanisms on top of a latent image representation provided by a standard, black-box model. This approach is based on a locality assumption: that the latent representation of an object part encodes primarily information about the corresponding image region. In this work, we test this basic assumption, measuring intra-object leakage in vision models using part-based attribute annotations. Through a comprehensive experimental evaluation, we show that modern pretrained vision transformers violate the locality assumption and exhibit a strong intra-object leakage, in which each part encodes information from the whole object, a visual metonymy that compromises the faithfulness of attention-based interpretable-by-design methods for part-based reasoning, ultimately rendering them uninterpretable. In addition, we establish an upper bound using a two-stage approach that prevents leakage by design. We then show that this inherently disentangled feature extraction improves attribute-driven part discovery on a variety of tasks, confirming the practical impact of intra-object leakage. Our results uncover a neglected issue affecting the interpretability of part-based representations, such as those in CBMs relying on part-centric concepts, highlighting that two-stage approaches offer a promising way to mitigate it.

Label noise remains a critical bottleneck for the generalization of supervised deep learning models, particularly when errors are structured rather than random. Standard robust training methods often fail in the presence of such semantically proximal classification errors. This work presents an architecture-agnostic Lipschitz-constant Bayesian header that can be integrated into feature extractors such as vision transformers, yielding the bi-Lipschitz-constrained Bayesian Vision Transformer (LipB-ViT). In contrast to conventional Bayesian layers, our approach enforces spectral normalization on both the mean and log-variance of the variational weights, which promotes calibrated predictive uncertainty and mitigates noise amplification. We further propose a novel metric to jointly capture uncertainty and confidence across misclassification rates, as well as an adaptive arithmetic-mean fusion scheme that combines feature-space proximity with predictive uncertainty to detect corrupted labels outperforming the state of the art k-nearest neighbor based identification methods by more than 7% reaching a recall of more than 0.93 at 15% semantically misclassified labels. Although computational costs increase due to Monte Carlo sampling, the method offers plug-and-play compatibility with pre-trained backbones and consistent hyperparameters across domains, suggesting strong utility for high-stakes applications with variable annotation reliability. The stabilized confidence estimates serve as the foundation for an analysis pipeline that jointly assesses dataset quality and label noise, yielding a second novel metric for their combined quantification. Lastly, we systematically evaluate LipB-ViT under both structured (adversarial) and unstructured noise at inference time, demonstrating its robustness in realistic high-noise and attack scenarios. We compare its performance against baseline methods.

Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either handle quantization post-training or suppress large activations during training; however, aggressively restricting outliers in vision models can lead to a poorer trade-off between full-precision and quantized accuracy. We argue that rather than simply suppressing outliers, the training objective should control the structural amplification that makes them harmful. To this end, we introduce Colinearity-Decay (CD), a structural regularizer for ordered matrix pairs within Transformer blocks. CD penalizes detrimental cross-matrix alignment and mitigates extreme activations without altering the architecture or task loss. Applied as a decoupled update, CD is non-invasive and introduces minimal training overhead. Across ImageNet-1K pre-training, COCO detection, and downstream fine-tuning, CD consistently boosts quantized accuracy across multiple pipelines while preserving, or even improving, full-precision performance. Ultimately, our results demonstrate that structural regularization effectively prepares vision Transformers for low-bit deployment with zero inference-time overhead.

In this paper, we present Generative Language-Image Pre-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) Simplicity: a single transformer jointly models visual and textual tokens; (2) Scalability: it scales effectively with both data and model size; and (3) Performance: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.

Aerosol Optical Depth (AOD) retrieval is essential for Earth observation, supporting applications from air quality monitoring to climate studies. Conventional physics-based AOD retrieval methods formulate the problem as a pixel-wise inversion, relying on radiative transfer modeling, memory-intensive look-up tables, and auxiliary meteorological data. While recent data-driven approaches have shown promise, many fail to exploit the spatial-spectral coherence of hyperspectral imagery, leading to spatially inconsistent and noise-sensitive retrievals. We present the first study exploring Foundation AI models for AOD retrieval and propose ViTCG, a Vision Transformer with Channel-wise Grouping-based spatial regression framework that reduces retrieval bias and error. ViTCG uses hyperspectral top-of-atmosphere radiance as input and jointly models spatial context and spectral information. Validation with PACE radiance observations demonstrates a 62% reduction in mean squared error compared to state-of-the-art foundation models, including Prithvi, and produces spatially coherent AOD fields.

Plant phenology-the study of recurrent life cycle events-is essential for understanding ecosystem dynamics and their responses to climate change impacts. While Unmanned Aerial Vehicles (UAVs) and near-surface cameras enable high-resolution monitoring, identifying plant species across time remains computationally challenging. State-of-the-art approaches, specifically Multi-Temporal Convolutional Networks (CNNs), rely on rigid multi-branch architectures that scale poorly with longer time series and require large spatial context windows. In this paper, we present an extensive study on optimizing Vision Transformers (ViTs) for efficient spatio-temporal vegetation pixel classification. We conducted a comprehensive ablation study analyzing seven key design dimensions, including: (i) data normalization; (ii) spectral arrangement; (iii) boundary handling; (iv) spatial context window shape and size; (v) tokenization strategies; (vi) positional encoding; and (vii) feature aggregation strategies. Our method was evaluated on two datasets from the Brazilian Cerrado biome, Serra do Cipó (aerial imagery) and Itirapina (near-surface imagery). Experimental results demonstrate that our ViT approach offers a substantial improvement in computational efficiency while maintaining competitive classification performance. Notably, our ViT reduces Floating Point Operations (FLOPs) by an order of magnitude and maintains constant parameter complexity regardless of the time series length, whereas the CNN baseline scales linearly. Our findings confirm that ViTs are a robust, scalable solution for resource-constrained phenological monitoring systems.

Probing frozen vision transformers typically uses permutation-invariant aggregation (GAP or $\texttt{[CLS]}$), treating patch tokens as an unstructured set. Content-dependent probes such as self-attention are useful accuracy controls, but they do not expose a fixed token schedule or fixed position weights for auditing. We introduce SSMProbe, a probe of frozen vision transformers that learns a Sinkhorn patch route and reads it with a diagonal S4 decoder. The decoder's causal linear time-invariant (LTI) recurrence yields fixed position coefficients, exposing how patch arrangement interacts with sequential weighting. Held-out spatial predictability measures route organization beyond a location-bias null. On CUB and Cars, MAE, BEiT, DINOv2, and supervised ViT yield spatially organized routes with distinct readout profiles: DINOv2 is $\texttt{[CLS]}$-dominant, while MAE benefits from learned routing over fixed scans. On MAE/ImageNet, Sinkhorn reaches 70.33% accuracy, 5.55 percentage points above the strongest fixed scan.

FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult. We identify three main obstacles to integer-only FlashAttention: (1) scale explosion during tile-wise accumulation, (2) inefficient shift-based exponential operations on GPUs, and (3) quantization granularity constraints requiring uniform scales for integer comparison. To address these challenges, we propose QFlash, an end-to-end integer FlashAttention design that performs softmax entirely in the integer domain and runs as a single Triton kernel. On seven attention workloads from ViT, DeiT, and Swin models, QFlash achieves up to 6.73$\times$ speedup over I-ViT and up to 8.69$\times$ speedup on Swin, while reducing energy consumption by 18.8% compared to FP16 FlashAttention, without sacrificing Top-1 accuracy on ViT/DeiT and remaining competitive on Swin under per-tensor quantization. Our code is publicly available at https://github.com/EfficientCompLab/qflash.

Existing attention accelerators often trade exact softmax semantics, depend on fused Tensor Core kernels, or incur sequential depth that limits FP32 throughput on long sequences. We present ELSA, an algorithmic reformulation of online softmax attention that (i)~preserves exact softmax semantics in real arithmetic with a provable $\mathcal{O}(u\log n)$ FP32 relative error bound; (ii)~casts the online softmax update as a prefix scan over an associative monoid $(m,S,W)$, yielding $O(n)$ extra memory and $O(\log n)$ parallel depth; and (iii)~is Tensor-Core independent, implemented in Triton and CUDA C++, and deployable as a drop-in replacement requiring no retraining or weight modification. Unlike FlashAttention-2/3, which rely on HMMA/GMMA Tensor Core instructions and provide no compatible FP32 path, ELSA operates identically on A100s and resource-constrained edge devices such as Jetson TX2 -- making it the only hardware-agnostic exact-attention kernel that reduces parallel depth to $O(\log n)$ at full precision. On A100 FP32 benchmarks (1K--16K tokens), ELSA delivers $1.3$--$3.5\times$ speedup over memory-efficient SDPA and $1.97$--$2.27\times$ on BERT; on Jetson TX2, ELSA achieves $1.5$--$1.6\times$ over Math (64--900 tokens), with $17.8$--$20.2\%$ throughput gains under LLaMA-13B offloading at $\ge$32K. In FP16, ELSA approaches hardware-fused baselines at long sequences while retaining full FP32 capability, offering a unified kernel for high-precision inference across platforms. Our code and implementation are available at https://github.com/ming053l/ELSA.

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded. Probing a frozen ViT-B/16 layerwise for two complementary properties, local patch boundaries (BSDS500) and per-patch depth (NYU Depth V2), reveals a clear hierarchy: boundary structure becomes linearly decodable at layers 5-6 (AP = 0.833), while depth, which requires integrating global cues, peaks two to three layers later at layer 8 (MAE = 0.0875). Both signals collapse at the final classification layer, and random-weight controls confirm the encodings are learned rather than architectural. Causal interventions add specificity: ablating the single direction a linear depth probe reads degrades depth decoding by up to 165%, while ablating any other direction changes it by less than 1%. Targeted activation patching along that direction shows the depth signal is partially re-derived at each layer rather than passively carried in the residual stream, with mid-layer interventions persisting most strongly downstream. The result is that a classification-trained ViT develops an actively maintained spatial hierarchy that mirrors the early-to-late progression observed in the primate visual cortex.

Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained vision models can be leveraged to learn distortion-robust representations, which can then be effectively applied to downstream tasks operating on distorted observations. In particular, we propose an asymmetric knowledge distillation framework in which both teacher and student are initialized from the same pretrained Vision Transformer but receive different views of each image: the teacher processes clean images, while the student sees their distorted versions. We introduce multi-level distillation that aligns global embeddings, patch-level features, and attention maps and show that the student is able to approximate clean-image representations despite never directly accessing clean data. We evaluate our approach on image classification tasks across several datasets and under various distortions, consistently outperforming existing alternatives for the same amount of human supervision.

Brain tumors represent one of the most critical neurological conditions, where early and accurate diagnosis is directly correlated with patient survival rates. Manual interpretation of Magnetic Resonance Imaging (MRI) scans is time-intensive, subject to inter-observer variability, and demands significant specialist expertise. This paper proposes a deep learning framework for automated four-class brain tumor classification distinguishing glioma, meningioma, pituitary tumor, and healthy brain tissue from a dataset of 7,023 MRI scans. The proposed system employs a Vision Transformer (ViT-B/16) pretrained on ImageNet-21k as the backbone, augmented with a clinically motivated preprocessing and training pipeline. Contrast Limited Adaptive Histogram Equalization (CLAHE) is applied to enhance local contrast and accentuate tumor boundaries invisible to standard normalization. A two-stage fine-tuning strategy is adopted: the classification head is warmed up with the backbone frozen, followed by full fine-tuning with discriminative learning rates. MixUp and CutMix augmentation is applied per batch to improve generalization. Exponential Moving Average (EMA) of weights and Test-Time Augmentation (TTA) further stabilize and boost performance. Attention Rollout visualization provides clinically interpretable heatmaps of the brain regions driving each prediction. The proposed model achieves a test accuracy of 99.29%, macro F1-score of 99.25%, and perfect recall on both healthy and meningioma classes, outperforming all CNN-based baselines

With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViTs in handling resolution sensitivity and their relative neglect of local information, the ability of ViT-based methods to predict details and handle arbitrary-resolution images is still weaker than that of CNN-based methods. To address these shortcomings, we propose MLG-Stereo, a systematic pipeline-level design that extends global modeling beyond the encoder stage. First, we propose a Multi-Granularity Feature Network to effectively balance global context and local geometric information, enabling comprehensive feature extraction from images of arbitrary resolution and bridging the gap between training and inference scales. Then, a Local-Global Cost Volume is constructed to capture both locally-correlated and global-aware matching information. Finally, a Local-Global Guided Recurrent Unit is introduced to iteratively optimize the disparity locally under the guidance of global information. Extensive experiments are conducted on multiple benchmark datasets, demonstrating that our MLG-Stereo exhibits highly competitive performance on the Middlebury and KITTI-2015 benchmarks compared to contemporaneous leading methods, and achieves outstanding results in the KITTI-2012 dataset.

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational models like DINO are constrained to low-resolution processing. A recent foveal-inspired transformer achieves resolution agnosticism by iteratively processing a fixed-size context of multi-zoom patches. This model demonstrated promising results via supervised learning, utilizing a sequential, recurrent-like process without backpropagation through time. To unlock its potential as a foundational backbone, we introduce a novel sequential-to-global SSL framework based on DINO's self-distillation objective. Supported by an efficient integral-image patch extraction method, our approach enables large-scale pretraining for image-size agnostic vision encoders. We achieve competitive performance on ImageNet-1K and downstream classification tasks, maintaining a constant computational budget regardless of input resolution.

Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode. In contrast, biological neural systems address this through fast synaptic updates that form transient associative memories during inference, a property known as Hebbian plasticity. In this paper, we conduct an empirical study of Hebbian Fast-Weight (HFW) modules integrated into multiple transformer backbones, including ViT-Small, DeiT-Small, and Swin-Tiny. We evaluate six model variants: ViT, DeiT, Swin, ViT-Hebbian, DeiT-Hebbian, and Swin-Hebbian on 5-way 1-shot and 5-way 5-shot classification tasks using the Omniglot benchmark under a Prototypical Network meta-learning framework. We propose a single module placement strategy for Swin-Tiny in which one HFW module is applied to the final stage feature map after all hierarchical stages have completed. This design avoids the training instability caused by placing separate Hebbian modules at each stage and achieves the highest test accuracy across all six models (96.2% at 1-shot; 99.2% at 5-shot), outperforming its non-Hebbian baseline by $+0.3$ percentage points at 1-shot. We analyze the interaction between Swin's shifted window inductive bias and episode-level Hebbian binding, discuss why per-block placement fails for ViT and DeiT variants in a low-data regime, and situate the results within the wider literature on fast and slow-weight meta-learning.

Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger location during inference to maximize trigger attention. However, they overlook the self-attention mechanism in ViTs, which captures long-range dependencies across patches. In this work, we observe that a patch-wise trigger can achieve high attack effectiveness when activating backdoors across neighboring patches, a phenomenon we term the Trigger Radiating Effect (TRE). We further find that inter-patch trigger insertion during training can synergistically enhance TRE compared to single-patch insertion. Prior ViT-specific attacks that maximize trigger attention often sacrifice visual and attention stealthiness, making them detectable. Based on these insights, we propose PASTA, a twofold stealthy patch-wise backdoor attack in both pixel and attention domains. PASTA enables backdoor activation when the trigger is placed at arbitrary patches during inference. To achieve this, we introduce a multi-location trigger insertion strategy to enhance TRE. However, preserving stealthiness while maintaining strong TRE is challenging, as TRE is weakened under stealthy constraints. We therefore formulate a bi-level optimization problem and propose an adaptive backdoor learning framework, where the model and trigger iteratively adapt to each other to avoid local optima. Extensive experiments show that PASTA achieves 99.13% attack success rate across arbitrary patches on average, while significantly improving visual and attention stealthiness (144.43x and 18.68x) and robustness (2.79x) against state-of-the-art ViT defenses across four datasets, outperforming CNN- and ViT-based baselines.

For state-of-the-art image understanding, Vision Transformers (ViTs) have become the standard architecture but their processing diverges substantially from human attentional characteristics. We investigate whether this cognitive gap can be shrunk by fine-tuning the self-attention weights of Google's ViT-B/16 on human saliency fixation maps. To isolate the effects of semantically relevant signals from generic human supervision, the tuned model is compared against a shuffled control. Fine-tuning significantly improved alignment across five saliency metrics and induced three hallmark human-like biases: tuning reversed the baseline's anti-human large-object bias toward small-objects, amplified the animacy preference and diminished extreme attention entropy. Bayesian parity analysis provides decisive to very-strong evidence that this cognitive alignment comes at no cost to the model's original classification performance on in- (ImageNet), corrupted (ImageNet-C) and out-of-distribution (ObjectNet) benchmarks. An equivalent procedure applied to a ResNet-50 Convolutional Neural Network (CNN) instead degraded both alignment and accuracy, suggesting that the ViT's modular self-attention mechanism is uniquely suited for dissociating spatial priority from representational logic. These findings demonstrate that biologically grounded priors can be instilled as a free emergent property of human-aligned attention, to improve transformer interpretability.

Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present the first theoretical analysis of adversarial training under simplified ViT architectures. We show that, when trained under a signal-to-noise ratio that satisfies a certain condition and within a moderate perturbation budget, adversarial training enables ViTs to achieve nearly zero robust training loss and robust generalization error under certain regimes. Remarkably, this leads to strong generalization even in the presence of overfitting, a phenomenon known as benign overfitting, previously only observed in CNNs (with adversarial training). Experiments on both synthetic and real-world datasets further validate our theoretical findings.