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

CardsList

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

  1. DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models

    Jun 12, 2025Shicheng Yin, Kaixuan Yin, Yang Liu +2Vision Foundation ModelsEfficient ViTs

  2. Segment Anything for Dendrites from Electron Microscopy

    Nov 4, 2024Zewen Zhuo, Ilya Belevich, Ville Leinonen +4Image SegmentationVision Foundation Models