English
Related papers

Related papers: Learning to Merge Tokens in Vision Transformers

200 papers

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

Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited their application specially in resource-constrained settings.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Wentao Zhu

Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Yikai Wang , Xinghao Chen , Lele Cao , Wenbing Huang , Fuchun Sun , Yunhe Wang

Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However, the high inference computation cost poses a new challenge.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-12 Jiawei Chen , Lin Chen , Jiang Yang , Tianqi Shi , Lechao Cheng , Zunlei Feng , Mingli Song

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

As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vision Transformers (ViTs) require complex self-attention…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Junrui Xiao , Zhikai Li , Lianwei Yang , Qingyi Gu

The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Benjamin Bergner , Christoph Lippert , Aravindh Mahendran

The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Zherui Zhang , Rongtao Xu , Jie Zhou , Changwei Wang , Xingtian Pei , Wenhao Xu , Jiguang Zhang , Li Guo , Longxiang Gao , Wenbo Xu , Shibiao Xu

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Haicheng Wang , Zhemeng Yu , Gabriele Spadaro , Chen Ju , Victor Quétu , Shuai Xiao , Enzo Tartaglione

Patch-based models, e.g., Vision Transformers (ViTs) and Mixers, have shown impressive results on various visual recognition tasks, alternating classic convolutional networks. While the initial patch-based models (ViTs) treated all patches…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Hyunwoo Kang , Sangwoo Mo , Jinwoo Shin

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Xinjian Wu , Fanhu Zeng , Xiudong Wang , Xinghao Chen

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Weihao Yu , Mi Luo , Pan Zhou , Chenyang Si , Yichen Zhou , Xinchao Wang , Jiashi Feng , Shuicheng Yan

To build a cross-modal latent space between 3D human motion and language, acquiring large-scale and high-quality human motion data is crucial. However, unlike the abundance of image data, the scarcity of motion data has limited the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Qing Yu , Mikihiro Tanaka , Kent Fujiwara

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Louis Fabrice Tshimanga , Andrea Zanola , Federico Del Pup , Manfredo Atzori

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 Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Mingqian Ji , Shanshan Zhang , Jian Yang

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Shibo Jie , Yehui Tang , Jianyuan Guo , Zhi-Hong Deng , Kai Han , Yunhe Wang

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and…

Machine Learning · Computer Science 2026-01-21 Richard E. Turner
‹ Prev 1 3 4 5 6 7 10 Next ›