English
Related papers

Related papers: Re-purposing SAM into Efficient Visual Projectors …

200 papers

Large Language Models (LLMs) demonstrate strong capabilities in broad knowledge representation, yet they are inherently deficient in pixel-level perceptual understanding. Although the Segment Anything Model (SAM) represents a significant…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hao Wang , Limeng Qiao , Zequn Jie , Zhijian Huang , Chengjian Feng , Qingfang Zheng , Lin Ma , Xiangyuan Lan , Xiaodan Liang

Large Vision--Language Models (LVLMs) hold great promise for advancing optical remote sensing (RS) analysis, yet existing reasoning segmentation frameworks couple linguistic reasoning and pixel prediction through end-to-end supervised…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Xu Zhang , Junyao Ge , Yang Zheng , Kaitai Guo , Jimin Liang

Referring image segmentation (RIS) aims to precisely segment referents in images through corresponding natural language expressions, yet relying on cost-intensive mask annotations. Weakly supervised RIS thus learns from image-text pairs to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Qiyuan Dai , Sibei Yang

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Tianshuo Peng , Zuchao Li , Lefei Zhang , Hai Zhao , Ping Wang , Bo Du

The computational expense of redundant vision tokens in Large Vision-Language Models (LVLMs) has led many existing methods to compress them via a vision projector. However, this compression may lose visual information that is crucial for…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Ze Feng , Jiang-jiang Liu , Sen Yang , Lingyu Xiao , Zhibin Quan , Zhenhua Feng , Wankou Yang , Jingdong Wang

Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Wenxuan Wang , Jing Liu , Xingjian He , Yisi Zhang , Chen Chen , Jiachen Shen , Yan Zhang , Jiangyun Li

The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Shun Qian , Bingquan Liu , Chengjie Sun , Zhen Xu , Baoxun Wang

Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Dongchen Lu , Yuyao Sun , Zilu Zhang , Leping Huang , Jianliang Zeng , Mao Shu , Huo Cao

Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent models that rely on powerful pretrained vision encoders and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Bo Peng , Xia Ning , Zhihui Zhu

The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Yonglin Li , Jing Zhang , Xiao Teng , Long Lan , Xinwang Liu

The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Wei Tang , Xuejing Liu , Yanpeng Sun , Zechao Li

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Senqiao Yang , Junyi Li , Xin Lai , Bei Yu , Hengshuang Zhao , Jiaya Jia

Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computational requirements. In particular, the massive amount of…

Machine Learning · Computer Science 2026-04-14 Surendra Pathak , Bo Han

Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions. Despite the overwhelming progress, it still remains challenging for current approaches to perform well on cases with various…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Yajie Liu , Pu Ge , Haoxiang Ma , Shichao Fan , Qingjie Liu , Di Huang , Yunhong Wang

The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visual Tokenization, trained by self-supervised reconstructive learning, compresses visual data by codebook in patch-level with marginal…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Jianyu Zhang , Li Zhang , Shijian Li

To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception significantly influence the precision of spatial reasoning,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Runpeng Yu , Xinyin Ma , Xinchao Wang

Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align and instance-specific visual signals; optimizing on such…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Tongfei Chen , Shuo Yang , Yuguang Yang , Linlin Yang , Runtang Guo , Changbai Li , He Long , Chunyu Xie , Dawei Leng , Baochang Zhang

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Shengqiong Wu , Hao Fei , Xiangtai Li , Jiayi Ji , Hanwang Zhang , Tat-Seng Chua , Shuicheng Yan

Segment Anything Model (SAM) represents a large-scale segmentation model that enables powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in zero-shot, it requires user-provided prompts for each target…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Kosuke Sakurai , Ryotaro Shimizu , Masayuki Goto

The availability of real-time semantics greatly improves the core geometric functionality of SLAM systems, enabling numerous robotic and AR/VR applications. We present a new methodology for real-time semantic mapping from RGB-D sequences…

Computer Vision and Pattern Recognition · Computer Science 2023-10-16 Jingwen Wang , Juan Tarrio , Lourdes Agapito , Pablo F. Alcantarilla , Alexander Vakhitov