English
Related papers

Related papers: SWAT: Spatial Structure Within and Among Tokens

200 papers

Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Marius Aasan , Odd Kolbjørnsen , Anne Schistad Solberg , Adín Ramirez Rivera

Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Ryan Grainger , Thomas Paniagua , Xi Song , Naresh Cuntoor , Mun Wai Lee , Tianfu Wu

Accurate representation of the multiscale features in spatiotemporal physical systems using vision transformer (ViT) architectures requires extremely long, computationally prohibitive token sequences. To address this issue, we propose two…

Machine Learning · Computer Science 2024-12-31 Pei Zhang , M. Paul Laiu , Matthew Norman , Doug Stefanski , John Gounley

Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Hsiang-Wei Huang , Wenhao Chai , Kuang-Ming Chen , Cheng-Yen Yang , Jenq-Neng Hwang

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Aram Davtyan , Yusuf Sahin , Yasaman Haghighi , Sebastian Stapf , Pablo Acuaviva , Alexandre Alahi , Paolo Favaro

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Young Kyung Kim , J. Matías Di Martino , Guillermo Sapiro

In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Boyu Chen , Peixia Li , Baopu Li , Chuming Li , Lei Bai , Chen Lin , Ming Sun , Junjie Yan , Wanli Ouyang

The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Jakob Drachmann Havtorn , Amelie Royer , Tijmen Blankevoort , Babak Ehteshami Bejnordi

Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these advancements are not solely attributable to novel feature…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Xiaowei Hu , Min Shi , Weiyun Wang , Sitong Wu , Linjie Xing , Wenhai Wang , Xizhou Zhu , Lewei Lu , Jie Zhou , Xiaogang Wang , Yu Qiao , Jifeng Dai

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Martine Hjelkrem-Tan , Marius Aasan , Gabriel Y. Arteaga , Adín Ramírez Rivera

Vision Transformers have emerged as powerful, scalable and versatile representation learners. To capture both global and local features, a learnable [CLS] class token is typically prepended to the input sequence of patch tokens. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Alexis Marouani , Oriane Siméoni , Hervé Jégou , Piotr Bojanowski , Huy V. Vo

Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which models relationships…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Jaihyun Lew , Soohyuk Jang , Jaehoon Lee , Seungryong Yoo , Eunji Kim , Saehyung Lee , Jisoo Mok , Siwon Kim , Sungroh Yoon

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Youwei Liang , Chongjian Ge , Zhan Tong , Yibing Song , Jue Wang , Pengtao Xie

Image tokenizers map images to sequences of discrete tokens, and are a crucial component of autoregressive transformer-based image generation. The tokens are typically associated with spatial locations in the input image, arranged in raster…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Carlos Esteves , Mohammed Suhail , Ameesh Makadia

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Dong Lao , Yangchao Wu , Tian Yu Liu , Alex Wong , Stefano Soatto

We present a novel framework, Spatial Pyramid Attention Network (SPAN) for detection and localization of multiple types of image manipulations. The proposed architecture efficiently and effectively models the relationship between image…

Computer Vision and Pattern Recognition · Computer Science 2021-01-15 Xuefeng Hu , Zhihan Zhang , Zhenye Jiang , Syomantak Chaudhuri , Zhenheng Yang , Ram Nevatia

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 Hezheng Lin , Xing Cheng , Xiangyu Wu , Fan Yang , Dong Shen , Zhongyuan Wang , Qing Song , Wei Yuan

Since the introduction of Vision Transformer (ViT), patchification has long been regarded as a de facto image tokenization approach for plain visual architectures. By compressing the spatial size of images, this approach can effectively…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Feng Wang , Yaodong Yu , Guoyizhe Wei , Wei Shao , Yuyin Zhou , Alan Yuille , Cihang Xie

Image inpainting has achieved remarkable progress and inspired abundant methods, where the critical bottleneck is identified as how to fulfill the high-frequency structure and low-frequency texture information on the masked regions with…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Haipeng Liu , Yang Wang , Meng Wang , Yong Rui

Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Zanlin Ni , Yulin Wang , Renping Zhou , Yizeng Han , Jiayi Guo , Zhiyuan Liu , Yuan Yao , Gao Huang
‹ Prev 1 2 3 10 Next ›