CoViT introduces a self‑supervised framework that enhances Vision Transformers with instance‑aware representations by leveraging geometry‑guided contrastive learning. It refines attention maps to generate instance masks and constructs triplets that mine the hardest intra‑ and inter‑instance examples, driving a contrastive loss that reduces intra‑instance variance while increasing inter‑instance margins. The method yields consistent AP gains of over 2 points on instance‑level tasks without requiring extra decoders or labels.
arXiv:2507.00754v3 Announce Type: replace Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the...
arXiv:2511. 19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.
arXiv:2604. 02327v2 Announce Type: replace-cross Abstract: Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation.
arXiv:2512. 20014v3 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects.
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ViTs.
The paper studies Graph-Guided Token Merging (G2TM), a module that reduces token count in Vision Transformers. It evaluates G2TM across multiple segmentation frameworks and decoder types, finding that its performance gains are tied to the encoder rather than the decoder. The authors report consistent reductions in GFLOPs (22‑47%) and throughput improvements (up to 74%) on ADE20K, with optimal hyperparameters depending mainly on backbone pre‑training and target dataset.
arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...
arXiv:2509. 06461v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments.
ViTAMINS is a method that incorporates synthetic hard negatives into unsupervised vision transformer pretraining to enhance representation quality. The approach is evaluated on ImageNet and a range of downstream tasks—including transfer learning, image retrieval, copy detection, and image/video segmentation—showing significant performance gains. The synthetic negatives also lead to emergent properties, such as representations that encode explicit semantic information and act as strong classifiers, improving over baselines by up to 11.3%.
arXiv:2608.29917v1 Announce Type: new Abstract: Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes...
arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...