Feature-Based Knowledge Distillation

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 18

Oct 7, 2026cs.LG

Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs

GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting, but they do not specify where the student should preserve the teacher's graph-induced geometry. We show that this omission leads to two spectral failure modes in the student's representation space. On sparse graphs, the student suffers from spectral underfit, missing high-energy teacher directions concentrated near boundary regions. On dense graphs, it suffers from spectral overfit, retaining spurious directions that the teacher has collapsed through aggregation. Motivated by an energy-weighted teacher-student alignment objective, we propose Graph Geometry-aware MLP (G^2MLP), a training-time distillation framework guided by Ollivier-Ricci curvature. Curvature identifies where the two spectral errors concentrate and is used to allocate supervision between prediction-level and representation-level alignment. The deployed model remains a standard MLP and requires no graph access at inference. Across node-classification benchmarks, G^2MLP consistently improves over graph-free distillation baselines, reduces the teacher-student rank gap in both regimes, and transfers without architectural changes to Graph Transformer teachers and link prediction.

Zhewei Chen, Hao Zhu, Jiaojiao Jiang +1

Australian National University · Data61, CSIRO · University of New South Wales

Knowledge Distillation Cross-Architecture Knowledge Distillation Feature-Based Knowledge Distillation

Oct 5, 2026cs.LG

Closing the Context Gap: Activation Alignment for Tabular In-Context Learning

Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that separate training from inference, these models must process all training examples in every forward pass, making each prediction expensive. Restricting the number of training examples reduces this cost but substantially degrades performance. Instead of discarding context, we propose activation alignment, a method that leverages the full context to teach a model how to behave when seeing only a subset. This is achieved by training a lightweight linear transformation on synthetic unlabeled data to map the intermediate activations of a data-constrained "student" (using partial context) toward those of a full-context "teacher" (using all data). Training the aligner requires no GPU and converges in seconds to minutes on commodity hardware. We evaluate on 38 classification datasets from the TabArena benchmark using the leading two tabular foundation models, TabPFN-3 and TabFM. Across all context budgets, the aligned student yields broad, statistically significant improvements over the unaligned baseline for both models. In low-data regimes, alignment recovers nearly half of the teacher's predictive advantage. The method provides a practical, low-overhead approach to achieving the inference speed of compact contexts while closing a significant fraction of the performance gap to the full-context teacher.

Yoel Zeldes

Independent Researcher

Tabular Foundation Models Tabular ICL Feature-Based Knowledge Distillation Representation Alignment

Oct 5, 2026cs.CV

Difference Feature Map Distillation: Transferring Inter-Sample Relational Knowledge Towards Efficient Transformer-Based Tracking

In autonomous driving perception, visual object tracking systems must satisfy stringent latency and power constraints while remaining robust in complex and dynamic environments. Although transformer-based trackers achieve state-of-the-art accuracy, their substantial computational and memory overheads hinder deployment on real-time, resource-constrained platforms. To move toward this goal, we propose Difference Feature Map Knowledge Distillation (DFM-KD), a novel relational distillation framework tailored for transformer-based visual object tracking. Unlike conventional feature distillation methods that minimize point-wise discrepancies (e.g., mean squared error) between teacher and student feature representations, DFM-KD transfers knowledge through inter-sample feature differences, explicitly aligning the relational structure of the feature space. By distilling how the teacher models appearance variation and consistency across samples, rather than enforcing similarity in absolute activations, DFM-KD enables the student to better capture the structural dynamics of visual changes within a batch. As a result, the distilled model exhibits enhanced feature robustness and improved tracking performance. Extensive experiments demonstrate that DFM-KD consistently outperforms conventional feature-level distillation methods in both tracking precision and success rates.

Zhicheng Ding, Xinyu Chu, Qing Tian

Department of Computer Science, Bowling Green State University, OH 43402, USA · Department of Computer Science, University of Alabama at Birmingham, AL 35294, USA

Visual Object Tracking Autonomous Driving Perception Relational Knowledge Distillation Feature-Based Knowledge Distillation

Sep 29, 2026cs.CV

Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features

Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typically assume that teacher and student features reside in structurally alignable representation spaces. However, this assumption does not hold when cross-modal features are structurally heterogeneous and lack clear unit-level correspondence, such as 2D spatial visual grids and 1D temporal audio sequences, thereby limiting the applicability of feature-level alignment. To address this challenge, we propose a cross-modal distillation framework that enables effective knowledge transfer across structurally heterogeneous feature spaces via a vector-quantized codebook. Specifically, teacher features are abstracted into a set of vector-form codes regardless of their original feature structure, and the selected codes serve as concept-level anchors for student learning. Code selection is guided by both task relevance and student compatibility, allowing the student to receive transferable teacher knowledge without requiring direct unit-level feature alignment. Experimental results across diverse cross-modal distillation scenarios demonstrate the effectiveness of the proposed framework on classification and semantic segmentation tasks.

Dae Ung Jo, Jongin Lim, YoungJoon Yoo +1

Kyungpook National University · AX/PI Center, Samsung Electronics · Chung-Ang University, SNUAILAB +1

Cross-Modal Knowledge Distillation Cross-Modal Alignment Feature-Based Knowledge Distillation

Sep 29, 2026cs.CV

SFE-VGGT: Source-Free VGGT Distillation for Event-Based Monocular Depth Estimation

Recent event-based depth estimation methods successfully transfer geometric priors from vision foundation models via cross-modal distillation. However, their reliance on synchronized RGB-event pairs or depth annotations during training severely restricts practical deployment. To overcome this bottleneck, we propose SFE-VGGT, a novel source-free framework that distills the geometric priors of VGGT to the event domain without any paired RGB observations. Our core idea is to reconstruct surrogate frames directly from the target event stream to act as a frozen geometric teacher, entirely eliminating the need for genuine source RGB data. Crucially, as these surrogate frames inherently yield imperfect and spatially varying supervision, directly distilling from them propagates artifacts. To resolve this, we introduce a novel reliability-aware distillation strategy. This includes Density-Aware Feature Distillation to emphasize informative event regions, and Confidence-Weighted Depth Distillation to dynamically regulate supervision based on relative teacher-student prediction confidence. Meanwhile, we propose a Cross-Frame Relational Consistency loss that enforces temporal geometric stability using reliable inter-frame correspondences, bypassing the need for temporally consistent teacher's depth. Extensive experiments demonstrate that, despite source-free, our SFE-VGGT closely matches the accuracy of RGB-dependent baselines under standard conditions and significantly surpasses them in challenging nighttime scenarios. Across MVSEC nighttime sequences, SFE-VGGT reduces the average 10 m depth error by 15.3% compared with EventVGGT. Moreover, our method exhibits robust zero-shot generalization across real-world datasets, proving that highly effective geometric priors can be transferred to event cameras using strictly source-free supervision.

Thai Duy Nguyen, Addison Lin Wang

Nanyang Technological University, Singapore.

Event-Based Vision Monocular Depth Estimation Data-Free Knowledge Distillation Feature-Based Knowledge Distillation Knowledge Distillation

Sep 29, 2026cs.CV

What Makes High-Magnification Knowledge Transferable? A Study of Cross-Resolution Distillation in Whole-Slide Imaging

Cross-resolution knowledge distillation aims to improve low-magnification whole- slide analysis by transferring high-magnification representations, yet the conditions for useful transfer remain unclear. We develop a decomposition-based analysis of teacher access, representation loss, and model excess, motivating three questions: whether (a) teacher targets help the task, (b) low-magnification students can predict them, and (c) slide models benefit from those predictions. We investigate them through controlled experiments across ten pathology cohorts spanning classifi- cation, grading, and survival prediction. In the main comparison, providing teacher regional means alongside native low-magnification features improves downstream performance in all ten cohorts. Direct prediction achieves lower reconstruction error than residual prediction, yet the predicted features underrepresent variation in the teacher targets. Moreover, better reconstruction does not consistently improve downstream scores, and retaining native features changes performance even when the predicted teacher features are held fixed. Together, these findings expose a gap between reconstructing teacher representations and realizing their downstream value. They challenge the sufficiency of reconstruction error as a measure of cross-resolution transfer and provide a diagnostic framework for examining where that transfer breaks down. Future distillation designs must account for both what students can predict and how slide models use those predictions.

Zhiyuan Yang, Jiahao Cheng, Mahdi S. Hosseini

Department of Computer Science and Software Engineering (CSSE) Concordia University Montreal, Canada · Department of Computer Science and Software Engineering (CSSE) Concordia University Montreal, Canada Mila – Quebec AI Institute Montreal, Canada

Feature-Based Knowledge Distillation Knowledge Distillation Whole-Slide Image Analysis

Sep 28, 2026cs.CV

The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation

Large visual foundation models have demonstrated remarkable transferability across a wide range of downstream tasks. To deploy such models efficiently, feature matching has become a popular knowledge distillation approach that transfers teacher representations to smaller student models without requiring labeled data. However, we show that the conventional feature matching objective with L2-distance is inherently biased toward reconstructing dominant spectral directions of the teacher representation, while under-optimizing low-variance directions that often contain task-relevant information. To address this, we propose Spectrum-Balanced Feature Matching, SpecMatch, a simple objective that adaptively emphasizes under-optimized spectral directions while preserving the relative importance of dominant directions. SpecMatch is easy to implement and introduces negligible computational overhead. Extensive experiments on image recognition demonstrate that SpecMatch consistently improves downstream adaptation across diverse tasks, including image classification, anomaly detection, medical image analysis, and domain generalization. In particular, SpecMatch outperforms conventional feature matching in 40 of 42 teacher--student and training-setting combinations, while consistently improving over the original student model in all settings. We further demonstrate that the proposed objective generalizes beyond vision, improving downstream performance across six protein understanding tasks.

Kuniaki Saito, Yoshitaka Ushiku

OMRON SINIC X Corporation

Representation Learning Vision Foundation Model Adaptation Feature-Based Knowledge Distillation Knowledge Distillation

Sep 27, 2026cs.CV

Position Aware Layer Queries for Test Time Training in Vision Language Models

Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing TTT methods for Vision-Language Models (VLMs) create supervision from several augmented views, each requiring forward (and often backward) passes through the entire VLM, incurring substantial computational cost. We observe that one forward pass with all the intermediate layer outputs already yields far more signal than the final embedding from all augmentations. We introduce Layer Query Network (LQN), a lightweight approach that can adapt a frozen VLM (teacher) in a single forward pass of the VLM via a small model (student). LQN uses Position-Aware Distillation (PAD) to mimic the teacher VLM's intermediate-layer spatial tokens by querying spatial coordinates of intermediate tokens. LQN additionally relies on Location Consistency Regularization (LCR), a self-supervision technique, replacing expensive O(H x W) image augmentation with O(1) coordinate sampling. Integrating these, LQN i) adapts and improves zero-shot CLIP ViT-B/16 by 9.8% Top-1 on OOD ImageNet, ii) outperforms the previous best GS-Bias on fine-grained classification by 3.9% Top-1, iii) achieves faster convergence than TPS for CLIP ResNet-50 (47 mins vs 55 mins), iv) generalizes adaptation to VLMs like SigLIP, EVA-CLIP, and CoCa, and lightweight students like MLP, ResNet, VGG, and v) extends to panoptic, instance, and semantic segmentation.

Rajat Modi, Priyank Pathak, Xin Liang +1

Institute of Artificial Intelligence University of Central Florida Orlando, FL 32816, USA

Test-Time Adaptation of VLMs VLM Distillation Test-Time Training Feature-Based Knowledge Distillation

Sep 14, 2026cs.CV

Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition

As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student model for enhancing the latter's performance. In this work, we reviewed the feature knowledge distillation for 3D-CNNs and observed that most feature distillation methods in video analysis are simple adaptations of those used in image analysis, often neglecting the differences of video features in the temporal dimension. To address this issue, we proposed Label-Guided Knowledge Distillation (LGKD) to guide the distillation of student model features using ground truth labels. Our method entails two components: sample-wise distillation and class-wise distillation, enabling the student model to learn feature representation of the teacher model at two levels. Sample-wise distillation utilizes label information and the teacher's probability distribution to guide the learning of features that significantly impact temporal accuracy while mitigating noise. Meanwhile, class-wise feature distillation employs a prototype network to further capture the relational knowledge among samples within the same category, enhancing the student's ability to learn higher-dimensional semantic information and improving model generalization. To demonstrate the effectiveness and superiority of our method, we conducted comprehensive experiments on two benchmark action recognition datasets, UCF101 and HMDB51, achieving competitive results.

Yanjiang Shi, Peng Zhao, Nan Qi +1

School of Computer Science and Technology, and with the National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Xi’an 710049, China

Video Understanding Human Activity Recognition 3D CNNs Relational Knowledge Distillation Feature-Based Knowledge Distillation Knowledge Distillation

Aug 12, 2026cs.CV

Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer

Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itself learned to suppress: repulsive and bias-aware objectives exist, but none exploits the teacher's own trajectory to identify what the student should avoid. We observe that the missing signal is already encoded in the teacher's optimization trajectory: features that an early-stage teacher emphasizes but that a converged teacher attenuates are precisely the shortcut directions worth pushing the student away from. We instantiate this observation as \textbf{A}nti-\textbf{S}hortcut \textbf{D}istillation (ASD), a push--pull KD framework that treats the converged teacher

\Tfinal

as a positive semantic anchor and an early-checkpoint teacher

\Tearly

as a temporal negative reference. ASD couples two losses: a temporal contrastive loss (

\Ltc

) that places the early-teacher feature as a same-sample negative against in-batch and memory-bank final-teacher features in an InfoNCE objective; and a shortcut suppression loss (

\Lss

) that penalizes student projection onto the top eigenvectors of

\E[\Dh\Dh^{\top}]

, the uncentered second-moment matrix of early-to-final feature displacements. Across 13 teacher--student pairs on CIFAR-100, ImageNet-100, and TinyImageNet, ASD attains the highest clean top-1 accuracy on more than 10 pairs and outperforms standard KD on 12. On CIFAR-100-C corruption robustness, ASD obtains the lowest mean Corruption Error (

86.1

,mCE) on the most challenging cross-architecture pair (WRN-40-2

\to

ShuffleNet-V2). Mechanistic diagnostics confirm the intended geometry: the ASD student is systematically anti-aligned with the shortcut direction, while its projection onto the robust subspace is substantially larger (

0.45

vs.\

0.12

).

Syed Muhammad Raza, Omer Tariq, Jeongbae Son

Perception AI, Neubility Inc., Seoul, South Korea

Shortcut Learning Feature-Based Knowledge Distillation Knowledge Distillation

Aug 8, 2026cs.LG

A Controlled Study of Feature-Based Knowledge Distillation Across Student Designs

Knowledge distillation trains a smaller student to match the outputs of a larger teacher. Feature-based methods also align intermediate representations, but this extra constraint may affect students differently. We study this question on CIFAR-100 using a ResNet-50 teacher, a width-controlled CustomResNet family and MobileNetV2 as a cross-design comparison. For each student, we evaluate each feature method against a matched logit-KD run using the same teacher, optimizer settings, training schedule and seed. We repeat the main comparisons across multiple seeds. Logit KD improved every tested student over its scratch baseline. Attention Transfer showed no clear relationship with size inside the CustomResNet family, but its average effect was negative for that family and positive for MobileNetV2. FitNets was below logit KD in all 15 paired runs. Within the constant-depth width sweep, its gap increased for wider students, although the different-depth w=48 student did not follow this trend. Finally, the same auxiliary coefficient produced different gradient scales across students, showing that a fixed coefficient does not create a uniform training condition.

Abhinand Balachandran, Praveen Prashant

Georgia Institute of Technology Atlanta, Georgia, USA

Cross-Architecture Knowledge Distillation Feature-Based Knowledge Distillation Knowledge Distillation

Jul 29, 2026cs.LG

CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation

Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression. The emergence of diverse model architectures has extended KD from homogeneous to heterogeneous settings. However, differences in architectural inductive biases between the teacher and student models often result in substantial representation discrepancies, limiting the effectiveness of direct knowledge transfer. Recently, redundancy suppression has offered a new perspective on heterogeneous KD by preserving cross-architecture invariance and reducing feature redundancy through decorrelation of teacher-student feature correlations. Nevertheless, this formulation may weaken useful structural information through uniform decorrelation, while a fixed coefficient may make the effective contribution of redundancy suppression sensitive to teacher-student pairs and training stages. To address these problems, Correlation Calibration-based Redundancy Suppression (CoCaRS) is proposed to better retain structural information while suppressing redundancy and reduce sensitivity to coefficient settings across teacher-student pairs and training stages. Specifically, CoCaRS calibrates feature decorrelation through Confusion Evidence Estimation (CEE) and Strength Allocation Control (SAC), which respectively capture reliable semantic relations for correlation estimation and preserve discriminative structure during decorrelation. Adaptive Coefficient Regulation (ACR) further regulates the contribution of the calibrated redundancy suppression objective according to its relative loss scale, reducing sensitivity to coefficient settings. Extensive experiments on CIFAR-100 and ImageNet-1K validate the effectiveness of CoCaRS in improving distillation performance and reducing sensitivity to coefficient settings. Code will be released soon.

Fengming Yu, Haiwei Pan, Kejia Zhang +3

College of Computer Science and Technology, Harbin Engineering University, Harbin, China

Cross-Architecture Knowledge Distillation Feature-Based Knowledge Distillation Knowledge Distillation

Jun 17, 2026cs.CV

Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring

Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring, a training curriculum for ViT feature-based knowledge distillation. By utilizing the teacher's intermediate feature maps as a sequence of progressively more difficult targets, our curriculum allows the student to build a foundational representation before tackling higher-level abstractions. Our results demonstrate that this paradigm significantly accelerates convergence through adaptive difficulty selection across various student model sizes and dataset scales. With our curriculum, the Dyna-DINO distilled ViT-S achieves 90.1% accuracy on ImageNet-100, a +12.24% improvement compared with baseline. On ImageNet-1K, Dyna-DINO achieves +3.9% and +6.09% improvement for the instance retrieval task on the Oxford and Paris datasets, +1.93% improvements on semantic segmentation task, as well as meaningful performance gain on classification task. Furthermore, the curriculum enables 25.1% savings in training FLOPs and 21% savings in training time on ImageNet-100 by implementing early-stopping for teacher inference during the initial stages of training. Code is available at https://github.com/KevinZ0217/Dyna-DINO

Jiaqi Zhang, Ashton Lee, Anthony Wong +3

Brown University · Rice University

Efficient ViTs Curriculum Learning Feature-Based Knowledge Distillation Knowledge Distillation

May 29, 2026cs.CV

CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference

Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clinical (target) images, hindering real-world deployment. Existing domain adaptation methods often ignore crucial semantic invariants, such as clinical concepts. While new foundation models like MONET can provide this semantic information as dense, probabilistic scores, this metadata is unavailable at test time, creating a deployment paradox for practical image-only screening tools. We address this gap by proposing CoFiDA-M, a privileged information framework that learns from concepts at training time but deploys as an image-only model. Our method trains a teacher network that uses MONET concept probabilities to guide a FiLM modulator, transforming visual features into a semantically

edited" feature space. A lightweight, image-only student is then trained to reproduce this edited representation, not just the teacher's final predictions. This distillation

bakes" the clinical reasoning into the student's weights. On a challenging multi-dataset benchmark, our image-only student significantly outperforms state-of-the-art approaches, especially in melanoma recall. Our work provides a practical and generalizable framework for leveraging noisy, probabilistic metadata as privileged information, demonstrating strong cross-dataset robustness and potential for real-world deployment beyond dermatology. Implementation code is available at: https://github.com/mmu-dermatology-research/CoFiDA.git

Nurjahan Sultana, Moi Hoon Yap, Xinqi Fan +1

Department of Computing and Mathematics, Manchester Metropolitan University Dalton Building, Chester Street, M1 5GD Manchester, UK

Skin Lesion Classification Medical Image Classification Cross-Domain Transfer Learning Learning Using Privileged Information Feature-Based Knowledge Distillation

May 29, 2026cs.LG

Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10

We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10. Across four teacher-student pairs (R50->R18, R34->R18, R50->R34, and R101->R34) we compare Logit-KD and Feature-KD under a strict evaluation protocol: hyperparameters and checkpoints are selected on a held-out validation split, selected configurations are re-run with five seeds, and the test set is used exclusively for final reporting. Beyond accuracy, we measure distillation fidelity directly via teacher-student agreement and KL divergence. We report four findings. First, the student-capacity pattern survives the corrected protocol at reduced magnitude: the only statistically significant gains occur for R34 students under Feature-KD (+0.19 and +0.21 pp, p<0.05), in two pairs whose teachers differ two-fold in parameters but not in accuracy, localizing the moderating variable on the student side, while no KD gain for R18 students is distinguishable from zero. Second, Feature-KD matches or outperforms Logit-KD in all four pairs, and its students land closer to the teacher's output distribution (KL at T=1) than Logit-KD students despite never observing teacher logits. Third, top-1 teacher-student agreement is flat across all pairs, decoupling fidelity from accuracy gains. Fourth, architecture dominates KD: correcting the ResNet stem for 32x32 inputs is worth +5.5 to +7.2 pp, more than 25x the largest KD gain. We also retract an attribution made in v1: a controlled re-run shows the reported gradient-clipping bug had no measurable effect, and v1's larger gains are explained by test-set selection. Code and results: github.com/umutonuryasar/kd-capacity-gap (tag v2.0).

Umut Onur Yasar

Teacher-Student Learning Feature-Based Knowledge Distillation Knowledge Distillation Image Classification

May 12, 2026cs.LG

Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer

While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial prefixes. The absence of class-discriminative patterns in partial data can significantly hinder a classifier's ability to generalize. This work uses knowledge distillation (KD) to equip partial time series classifiers with the generalization ability of their full-sequence counterparts. In KD, high-capacity teacher transfers supervision to aid student learning on the target task. Matching with teacher features has shown promise in closing the generalization gap due to limited parameter capacity. However, when the generalization gap arises from training-data differences (full versus partial), the teacher's full-context features can be an overwhelming target signal for the student's short-context features. To provide progressive, diverse, and collective teacher supervision, we propose Generative Diffusion Prior Distillation (GDPD), a novel KD framework that treats short-context student features as degraded observations of the target full-context features. Inspired by the iterative restoration capability of diffusion models, we learn a diffusion-based generative prior over teacher features. Leveraging this prior, we posterior-sample target teacher representations that could best explain the missing long-range information in the student features and optimize the student features to be minimally degraded relative to these targets. GDPD provides each student feature with a distribution of task-relevant long-context knowledge, which benefits learning on the partial classification task. Extensive experiments across earliness settings, datasets, and architectures demonstrate GDPD's effectiveness for full-to-partial distillation.

Nilushika Udayangani, Kishor Nandakishor, Marimuthu Palaniswami

Department of Electrical and Electronic Engineering University of Melbourne Parkville, VIC 3052, Australia

Time Series Classification Feature-Based Knowledge Distillation Knowledge Distillation

May 8, 2026cs.CV

Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed training stages, or complex optimization pipelines. In this work, we revisit the recently proposed Drifting Model objective and show that a single drifting loss can be directly used to simplify one step distillation. A key observation is that the pretrained diffusion teacher itself already provides a strong representation space. Unlike the original Drifting Model, which relies on an additional pretrained feature extractor, we use intermediate hidden states of the pretrained teacher model as the feature representation. This removes the need for training or introducing an extra representation network while preserving a semantically meaningful feature geometry for drifting. Furthermore, we introduce a lightweight mode coverage loss to mitigate mode collapse during distillation and encourage the student generator to cover diverse teacher-supported regions. Extensive experiments on ImageNet and SDXL demonstrate that our method achieves efficient one step generation with competitive image quality and diversity, achieving FID scores of 1.58 on ImageNet-64

\times

64 and 18.4 on SDXL, while substantially simplifying the overall distillation framework.

Yuan Zhang, Chenyi Li, Guoqing Ma +7

JD Explore Academy, China · The Hong Kong University of Science and Technology · Tsinghua University +1

Diffusion Model Distillation Diffusion Sampling Diffusion-Based Image Generation Feature-Based Knowledge Distillation Knowledge Distillation

Apr 28, 2026cs.CV

The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation

Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration cost, meaning equal iteration counts do not correspond to equal training budgets. It is therefore unclear whether reported gains reflect stronger distillation signals or simply greater compute. We show that iteration-based comparisons are misleading: when wall-clock compute is matched, canonical logit- and feature-based KD outperform recent segmentation-specific methods. Under extended training, feature-based distillation achieves state-of-the-art ResNet-18 performance on Cityscapes and ADE20K. A PSPNet ResNet-18 student closely approaches its ResNet-101 teacher despite using only one quarter of the parameters, reaching 99% of the teacher's mIoU on Cityscapes (79.0 vs 79.8) and 92% on ADE20K. Our results challenge the prevailing assumption that KD for segmentation requires task-specific mechanisms and suggest that scaling, rather than complex hand-crafted objectives, should guide future method design.

Muhammad Ali, Kevin Alexander Laube, Madan Ravi Ganesh +3

University of Freiburg · Bosch Center for Artificial Intelligence · Aleph Alpha Research +1

Image Segmentation Feature-Based Knowledge Distillation Knowledge Distillation Semantic Segmentation