English
Related papers

Related papers: BEiT v2: Masked Image Modeling with Vector-Quantiz…

200 papers

Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Ze Wang , Hao Chen , Benran Hu , Jiang Liu , Ximeng Sun , Jialian Wu , Yusheng Su , Xiaodong Yu , Emad Barsoum , Zicheng Liu

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Jin Li , Yaoming Wang , Xiaopeng Zhang , Bowen Shi , Dongsheng Jiang , Chenglin Li , Wenrui Dai , Hongkai Xiong , Qi Tian

Vision Transformers (ViTs) have shown significant promise in computer vision applications. However, their performance in few-shot learning is limited by challenges in refining token-level interactions, struggling with limited training data,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Mohammed Al-Habib , Zuping Zhang , Abdulrahman Noman

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Machine Learning · Computer Science 2024-07-24 Hiroyuki Tokunaga , Joel Nicholls , Daria Vazhenina , Atsunori Kanemura

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

Image and Video Processing · Electrical Eng. & Systems 2023-04-24 Lei Zhou , Huidong Liu , Joseph Bae , Junjun He , Dimitris Samaras , Prateek Prasanna

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Xinliang Zhang , Lei Zhu , Hangzhou He , Shuang Zeng , Ourui Fu , Jiakui Hu , Zhengjian Yao , Yanye Lu

Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…

Computation and Language · Computer Science 2023-04-07 Xing Wu , Guangyuan Ma , Peng Wang , Meng Lin , Zijia Lin , Fuzheng Zhang , Songlin Hu

In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Binzhe Li , Shurun Wang , Shiqi Wang , Yan Ye

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

CutMix is a popular augmentation technique commonly used for training modern convolutional and transformer vision networks. It was originally designed to encourage Convolution Neural Networks (CNNs) to focus more on an image's global…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Jihao Liu , Boxiao Liu , Hang Zhou , Hongsheng Li , Yu Liu

Masked Autoencoders (MAE) have been prevailing paradigms for large-scale vision representation pre-training. By reconstructing masked image patches from a small portion of visible image regions, MAE forces the model to infer semantic…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Hongwei Xue , Peng Gao , Hongyang Li , Yu Qiao , Hao Sun , Houqiang Li , Jiebo Luo

Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual modality is inherently continuous and high-dimensional, which…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Xiaoyuan Guo , Jiali Duan , C. -C. Jay Kuo , Judy Wawira Gichoya , Imon Banerjee

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Computation and Language · Computer Science 2025-04-15 Buu Phan , Brandon Amos , Itai Gat , Marton Havasi , Matthew Muckley , Karen Ullrich

Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Di Wu , Yixin Wan , Kai-Wei Chang

Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately from recognition, supervisedly learned without…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Tsung-Wei Ke , Sangwoo Mo , Stella X. Yu

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Ali Javidani , Mohammad Amin Sadeghi , Babak Nadjar Araabi

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Phat Nguyen , Ngai-Man Cheung

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

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

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jingfeng Yao , Yuda Song , Yucong Zhou , Xinggang Wang