English
Related papers

Related papers: PR-MIM: Delving Deeper into Partial Reconstruction…

200 papers

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We…

Image and Video Processing · Electrical Eng. & Systems 2022-10-04 Bardia Azizian , Ivan V. Bajić

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Junhao Du , Jialong Xue , Anqi Li , Jincheng Dai , Guo Lu

Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning offers significant savings, but existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Patrick Glandorf , Thomas Norrenbrock , Bodo Rosenhahn

Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. But their practical application is often hindered by the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Qi Li , Yanzhe Zhao , Yongxin Zhou , Yameng Wang , Yandong Yang , Yuanjia Zhou , Jue Wang , Zuojian Wang , Jinxiang Liu

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Jaemin Son , Sujin Choi , Inyong Yun

Knowledge distillation is an effective method for training lightweight vision models. However, acquiring teacher supervision for training samples is often costly, especially from large-scale models like vision transformers (ViTs). In this…

Machine Learning · Computer Science 2024-09-30 Seungwoo Son , Jegwang Ryu , Namhoon Lee , Jaeho Lee

Several imaging applications (vessels, retina, plant roots, road networks from satellites) require the accurate segmentation of thin structures for subsequent analysis. Discontinuities (gaps) in the extracted foreground may hinder…

Computer Vision and Pattern Recognition · Computer Science 2019-12-06 Hao Chen , Mario Valerio Giuffrida , Peter Doerner , Sotirios A. Tsaftaris

Many modern ViT backbones adopt spatial architectural designs, such as window attention, decomposed relative positional embeddings in SAM, and RoPE in DINOv3. Such architectures impose new challenges on token reduction, as the vast majority…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Wenyi Gong , Mieszko Lis

The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Zhirong Wu , Zihang Lai , Xiao Sun , Stephen Lin

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…

Computer Vision and Pattern Recognition · Computer Science 2019-03-21 Tongtong Zhao , Yuxiao Yan , Jinjia Peng , Huibing Wang , Xianping Fu

Few-sample compression aims to compress a big redundant model into a small compact one with only few samples. If we fine-tune models with these limited few samples directly, models will be vulnerable to overfit and learn almost nothing.…

Machine Learning · Computer Science 2022-01-11 Huanyu Wang , Junjie Liu , Xin Ma , Yang Yong , Zhenhua Chai , Jianxin Wu

Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…

Machine Learning · Computer Science 2025-06-17 Chaoyi Jiang , Sungwoo Kim , Lei Gao , Hossein Entezari Zarch , Won Woo Ro , Murali Annavaram

Vision Mamba has shown close to state of the art performance on computer vision tasks, drawing much interest in increasing it's efficiency. A promising approach is token reduction (that has been successfully implemented in ViTs). Pruning…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Mingjia Shi , Yuhao Zhou , Ruiji Yu , Zekai Li , Zhiyuan Liang , Xuanlei Zhao , Xiaojiang Peng , Shanmukha Ramakrishna Vedantam , Wangbo Zhao , Kai Wang , Yang You

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Sua Lee , Joonhun Lee , Myungjoo Kang

Artificial Intelligence in medicine is traditionally limited by the lack of massive training datasets. Foundation models, pre-trained models that can be adapted to downstream tasks with small datasets, could alleviate this problem.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Justin Engelmann , Miguel O. Bernabeu

We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens to the input embeddings in the spatial domain, in this paper,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Jiahao Xie , Wei Li , Xiaohang Zhan , Ziwei Liu , Yew Soon Ong , Chen Change Loy

Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks. In this work, we propose a unified view…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Zhiliang Peng , Li Dong , Hangbo Bao , Qixiang Ye , Furu Wei

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this…

Computation and Language · Computer Science 2026-02-26 Yuetao Chen , Xuliang Wang , Xinzhou Zheng , Ming Li , Peng Wang , Hong Xu

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Computation and Language · Computer Science 2024-02-27 Zekun Wang , Jingchang Chen , Wangchunshu Zhou , Haichao Zhu , Jiafeng Liang , Liping Shan , Ming Liu , Dongliang Xu , Qing Yang , Bing Qin

Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes. However, most of existing pruning algorithms only focus on the classification task defined on the source…

Computer Vision and Pattern Recognition · Computer Science 2022-02-24 Ruichen Li , Binghui Li , Qi Qian , Liwei Wang