English
Related papers

Related papers: ELIP: Efficient Discriminative Language-Image Pre-…

200 papers

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Chen Qian , Xinran Yu , Danyang Li , Guoxuan Chi , Zheng Yang , Qiang Ma , Xin Miao

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yuchen Liu , Yaoming Wang , Bowen Shi , Xiaopeng Zhang , Wenrui Dai , Chenglin Li , Hongkai Xiong , Qi Tian

Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Huafeng Kuang , Jie Wu , Xiawu Zheng , Ming Li , Xuefeng Xiao , Rui Wang , Min Zheng , Rongrong Ji

Contrastive image-text pre-trained models such as CLIP have shown remarkable adaptability to downstream tasks. However, they face challenges due to the high computational requirements of the Vision Transformer (ViT) backbone. Current…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Cheng-En Wu , Jinhong Lin , Yu Hen Hu , Pedro Morgado

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…

Computation and Language · Computer Science 2022-10-17 Tiannan Wang , Wangchunshu Zhou , Yan Zeng , Xinsong Zhang

Recent progress in Multimodal Large Language Models(MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Weihao Ye , Qiong Wu , Wenhao Lin , Yiyi Zhou

As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Mothilal Asokan , Kebin Wu , Fatima Albreiki

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Yanshu Li , Jianjiang Yang , Zhennan Shen , Ligong Han , Haoyan Xu , Ruixiang Tang

Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Natan Bagrov , Eugene Khvedchenia , Borys Tymchenko , Shay Aharon , Lior Kadoch , Tomer Keren , Ofri Masad , Yonatan Geifman , Ran Zilberstein , Tuomas Rintamaki , Matthieu Le , Andrew Tao

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

Machine Learning · Computer Science 2026-05-29 Yilin Feng , Ahmed Burak Gulhan , Mahmut Taylan Kandemir

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 An Yu , Ting Yu Tsai , Zhenfei Zhang , Weiheng Lu , Felix X. -F. Ye , Ming-Ching Chang

We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method that improves the efficiency of VLMs. Unlike MetaCLIP, our method does not need metadata for pruning, but selects text-image pairs to prune based on…

Machine Learning · Computer Science 2024-12-11 Mingliang Liang , Martha Larson

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Cheng Yang , Yang Sui , Jinqi Xiao , Lingyi Huang , Yu Gong , Chendi Li , Jinghua Yan , Yu Bai , Ponnuswamy Sadayappan , Xia Hu , Bo Yuan

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance…

Computer Vision and Pattern Recognition · Computer Science 2022-02-16 Junnan Li , Dongxu Li , Caiming Xiong , Steven Hoi

Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Sinuo Deng , Lifang Wu , Ge Shi , Lehao Xing , Meng Jian , Ye Xiang

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Yuhao Chen , Bin Shan , Xin Ye , Cheng Chen

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Kaicheng Yang , Jiankang Deng , Xiang An , Jiawei Li , Ziyong Feng , Jia Guo , Jing Yang , Tongliang Liu

Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Lijie Fan , Dilip Krishnan , Phillip Isola , Dina Katabi , Yonglong Tian

Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Dongsheng Chen , Chaofan Tao , Lu Hou , Lifeng Shang , Xin Jiang , Qun Liu

Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Wenhui Zhu , Xiwen Chen , Zhipeng Wang , Shao Tang , Sayan Ghosh , Xuanzhao Dong , Rajat Koner , Yalin Wang