Overview

Vision foundation models learn reusable visual representations from large image or video collections, often through self-supervised methods such as contrastive learning, masked prediction, and feature prediction, or through image-text and generative training. Researchers adapt them using frozen-feature probes, prompts, lightweight fine-tuning, distillation, and feature fusion for tasks ranging from classification and segmentation to depth, 3D geometry, and video understanding. These methods can transfer across tasks and domains, but specialized pretraining or adaptation can still be important in settings such as medical imaging, remote sensing, and scientific vision. A central open tension is whether broad pretrained representations can provide reliable spatial, temporal, and domain-robust understanding while remaining efficient and consistently evaluated.

Latest papers

152 papers16 papers in the last four weeks, up 7% on the four weeks before. 0.1% of all new papers.

Jun 12, 2025

DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models

The content-agnostic, fixed-grid tokenizers used by standard large-scale vision models like Vision Transformer (ViT) and Vision Mamba (Vim) represent a fundamental performance bottleneck, creating a trade-off between capturing fine-grained detail and suffering from redundant computation. To resolve this dilemma, we introduce DART, a fully differentiable Dynamic Adaptive Region Tokenizer. DART employs learnable region scores and quantile-based partitioning to create content-aware patches of varying sizes, intelligently allocating a higher token density to information-rich regions. The impact of this approach is profound: it unlocks a more intelligent scaling paradigm, where a DART-equipped DeiT-Small (22M parameters) matches the performance of a DeiT-Base (86M) with nearly double the inference speed by efficiently capturing high-resolution details in key regions. Furthermore, the principle of adaptive tokenization proves its generality with clear benefits in dense prediction and spatiotemporal video tasks. We argue that by resolving the tokenizer bottleneck at its source, adaptive tokenization is a key component for building the next generation of more efficient and capable foundation models for multimodal AI, robotics, and content generation. Code is available at https://github.com/HCPLab-SYSU/DART.
Nov 4, 2024

Segment Anything for Dendrites from Electron Microscopy

Segmentation of cellular structures in electron microscopy (EM) images is fundamental to analyzing the morphology of neurons and glial cells in the healthy and diseased brain tissue. Current neuronal segmentation applications are based on convolutional neural networks (CNNs) and do not effectively capture global relationships within images. Here, we present DendriteSAM, a vision foundation model based on Segment Anything, for interactive and automatic segmentation of dendrites in EM images. The model is trained on high-resolution EM data from healthy rat hippocampus and is tested on diseased rat and human data. Our evaluation results demonstrate better mask quality compared to the original and other fine-tuned models, leveraging the features learned during training. This study introduces the first implementation of vision foundation models in dendrite segmentation, paving the path for computer-assisted diagnosis of neuronal anomalies.