English
Related papers

Related papers: Understanding the Effect of using Semantically Mea…

200 papers

Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The artifacts correspond…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Timothée Darcet , Maxime Oquab , Julien Mairal , Piotr Bojanowski

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Li Yuan , Qibin Hou , Zihang Jiang , Jiashi Feng , Shuicheng Yan

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Yunjie Tian , Lingxi Xie , Jiemin Fang , Mengnan Shi , Junran Peng , Xiaopeng Zhang , Jianbin Jiao , Qi Tian , Qixiang Ye

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Yasmine Omri , Parth Shroff , Thierry Tambe

An end-to-end (E2E) visuomotor policy is typically treated as a unified whole, but recent approaches using out-of-domain (OOD) data to pretrain the visual encoder have cleanly separated the visual encoder from the network, with the…

Robotics · Computer Science 2025-05-15 Ruiyu Wang , Zheyu Zhuang , Shutong Jin , Nils Ingelhag , Danica Kragic , Florian T. Pokorny

Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a token. Generally, representing an image with more tokens…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yulin Wang , Rui Huang , Shiji Song , Zeyi Huang , Gao Huang

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while…

Computation and Language · Computer Science 2025-10-23 Yanhong Li , Zixuan Lan , Jiawei Zhou

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yiwei Guo , Shaobin Zhuang , Zhipeng Huang , Canmiao Fu , Chen Li , Jing Lyu , Yali Wang

Mechanistic interpretability seeks to uncover how internal components of neural networks give rise to predictions. A persistent challenge, however, is disentangling two often conflated notions: decodability--the recoverability of…

Machine Learning · Computer Science 2025-10-14 Lianghuan Huang , Yingshan Chang

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Taekyung Kim , Byeongho Heo , Dongyoon Han

What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either…

Multimedia · Computer Science 2025-08-07 Ali Vosoughi , Jing Bi , Pinxin Liu , Yunlong Tang , Chenliang Xu

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Chengzhi Mao , Lu Jiang , Mostafa Dehghani , Carl Vondrick , Rahul Sukthankar , Irfan Essa

We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Ting Pan , Lulu Tang , Xinlong Wang , Shiguang Shan

Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often producing $3$--$20\times$ fewer decoder tokens than subword tokenization. Yet…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Lv Tang , Tianyi Zheng , Yang Liu , Bo Li , Xingyu Li

Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When this occurs, they introduce a form of distribution shift at…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Ryan Ramos , Vladan Stojnić , Giorgos Kordopatis-Zilos , Yuta Nakashima , Giorgos Tolias , Noa Garcia

How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jinyeong Kim , Junhyeok Kim , Yumin Shim , Joohyeok Kim , Sunyoung Jung , Seong Jae Hwang

In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset can further boost the performance for the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Xinrong Hu , Dewen Zeng , Yawen Wu , Xueyang Li , Yiyu Shi

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Enming Zhang , Zhengyu Li , Yanru Wu , Jingge Wang , Yang Tan , Guan Wang , Yang Li , Xiaoping Zhang

Recently, vision transformers (ViTs) have achieved excellent performance on vision tasks by measuring the global self-attention among the image patches. Given $n$ patches, they will have quadratic complexity such as $\mathcal{O}(n^2)$ and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Jiquan Shan , Junxiao Wang , Lifeng Zhao , Liang Cai , Hongyuan Zhang , Ioannis Liritzis
‹ Prev 1 3 4 5 6 7 10 Next ›