English
Related papers

Related papers: ViTok-v2: Scaling Native Resolution Auto-Encoders …

200 papers

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

The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made in natural language processing and image representation…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Ziyun Zeng , Yixiao Ge , Zhan Tong , Xihui Liu , Shu-Tao Xia , Ying Shan

We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. Building on a pre-trained SSL encoder, we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Ming Gui , Johannes Schusterbauer , Timy Phan , Felix Krause , Josh Susskind , Miguel Angel Bautista , Björn Ommer

Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance;…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Bichen Wu , Chenfeng Xu , Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Zhicheng Yan , Masayoshi Tomizuka , Joseph Gonzalez , Kurt Keutzer , Peter Vajda

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Jiasen Lu , Liangchen Song , Mingze Xu , Byeongjoo Ahn , Yanjun Wang , Chen Chen , Afshin Dehghan , Yinfei Yang

Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale dataset and human-annotated labels, recent large-scale datasets…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Kodai Nakashima , Hirokatsu Kataoka , Asato Matsumoto , Kenji Iwata , Nakamasa Inoue

Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Qingyu Shi , Size Wu , Jinbin Bai , Kaidong Yu , Yujing Wang , Yunhai Tong , Xiangtai Li , Xuelong Li

In the evolving landscape of 6G networks, semantic communications are poised to revolutionize data transmission by prioritizing the transmission of semantic meaning over raw data accuracy. This paper presents a Vision Transformer…

Image and Video Processing · Electrical Eng. & Systems 2025-03-24 Muhammad Ahmed Mohsin , Muhammad Jazib , Zeeshan Alam , Muhmmad Farhan Khan , Muhammad Saad , Muhammad Ali Jamshed

Since being introduced in 2020, Vision Transformers (ViT) has been steadily breaking the record for many vision tasks and are often described as ``all-you-need" to replace ConvNet. Despite that, ViTs are generally computational,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Chuong H. Nguyen , Su Huynh , Vinh Nguyen , Ngoc Nguyen

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a small subset of parameters. While current PEFT methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Ting Liu , Xuyang Liu , Liangtao Shi , Zunnan Xu , Yue Hu , Siteng Huang , Yi Xin , Bineng Zhong , Donglin Wang

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Jiaying Zhu , Yurui Zhu , Xin Lu , Wenrui Yan , Dong Li , Kunlin Liu , Xueyang Fu , Zheng-Jun Zha

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Seungdong Yoa , Seungjun Lee , Hyeseung Cho , Bumsoo Kim , Woohyung Lim

Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Jongseong Bae , Susang Kim , Minsu Cho , Ha Young Kim

Conventional Vision Transformer simplifies visual modeling by standardizing input resolutions, often disregarding the variability of natural visual data and compromising spatial-contextual fidelity. While preliminary explorations have…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Limeng Qiao , Yiyang Gan , Bairui Wang , Jie Qin , Shuang Xu , Siqi Yang , Lin Ma

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Tianxiong Zhong , Xingye Tian , Boyuan Jiang , Xuebo Wang , Xin Tao , Pengfei Wan , Zhiwei Zhang

Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text has inspired scaling sequence…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Aristeidis Tsaris , Chengming Zhang , Xiao Wang , Junqi Yin , Siyan Liu , Moetasim Ashfaq , Ming Fan , Jong Youl Choi , Mohamed Wahib , Dan Lu , Prasanna Balaprakash , Feiyi Wang

Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scaling them to 2K…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Jingjing Ren , Wenbo Li , Zhongdao Wang , Haoze Sun , Bangzhen Liu , Haoyu Chen , Jiaqi Xu , Aoxue Li , Shifeng Zhang , Bin Shao , Yong Guo , Lei Zhu

We combine vision transformers with operator learning to solve diverse inverse problems described by partial differential equations (PDEs). Our approach, named ViTO, combines a U-Net based architecture with a vision transformer. We apply…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Oded Ovadia , Adar Kahana , Panos Stinis , Eli Turkel , George Em Karniadakis

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed…

Image and Video Processing · Electrical Eng. & Systems 2026-02-26 Wei Jiang , Yongqi Zhai , Jiayu Yang , Feng Gao , Ronggang Wang