English
Related papers

Related papers: Fast SAM2 with Text-Driven Token Pruning

200 papers

Segment Anything Model 2 (SAM 2) has emerged as a powerful tool for video object segmentation and tracking anything. Key components of SAM 2 that drive the impressive video object segmentation performance include a large multistage image…

The Segment Anything Model 2 (SAM2) is a powerful foundation model for promptable segmentation. However, its high computational and memory costs are a major barrier to deployment on resource-constrained devices. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Nicola Farronato , Florian Scheidegger , Mattia Rigotti , Cristiano Malossi , Michele Magno , Haotong Qin

Segment Anything Model 2 (SAM2) demonstrates exceptional performance in video segmentation and refinement of segmentation results. We anticipate that it can further evolve to achieve higher levels of automation for practical applications.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Zhiting Wang , Qiangong Zhou , Zongyang Liu

The Segment Anything Model 2 (SAM2) has recently demonstrated exceptional performance in zero-shot prompt segmentation for natural images and videos. However, when the propagation mechanism of SAM2 is applied to medical images, it often…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Yunhao Bai , Boxiang Yun , Zeli Chen , Qinji Yu , Yingda Xia , Yan Wang

Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Claudia Cuttano , Gabriele Trivigno , Gabriele Rosi , Carlo Masone , Giuseppe Averta

Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Zhang Jiaxing , Tang Hao

Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yuyuan Liu , Yuanhong Chen , Chong Wang , Junlin Han , Junde Wu , Can Peng , Jingkun Chen , Yu Tian , Gustavo Carneiro

Referring video object segmentation (RVOS) aims to segment objects in a video according to textual descriptions, which requires the integration of multimodal information and temporal dynamics perception. The Segment Anything Model 2 (SAM 2)…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Fu Rong , Meng Lan , Qian Zhang , Lefei Zhang

As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Samarth N Ramesh , Zhixue Zhao

The recent Segment Anything Model 2 (SAM2) has demonstrated exceptional capabilities in interactive object segmentation for both images and videos. However, as a foundational model on interactive segmentation, SAM2 performs segmentation…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Qiushi Yang , Yuan Yao , Miaomiao Cui , Liefeng Bo

Autonomous-driving perception systems require robust Multi-Object Tracking (MOT) to operate reliably in dynamic environments. MOT maintains consistent object identities across frames while preserving spatial accuracy. Recent foundation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Diogo Mendonça , Tiago Barros , Cristiano Premebida , Urbano J. Nunes

Few-shot segmentation aims to segment unseen object categories from just a handful of annotated examples. This requires mechanisms that can both identify semantically related objects across images and accurately produce segmentation masks.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Claudia Cuttano , Gabriele Trivigno , Giuseppe Averta , Carlo Masone

Accurate segmentation of neural structures in Electron Microscopy (EM) images is paramount for neuroscience. However, this task is challenged by intricate morphologies, low signal-to-noise ratios, and scarce annotations, limiting the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Zhenghua Li , Hang Chen , Zihao Sun , Kai Li , Xiaolin Hu

The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Benjamin Bergner , Christoph Lippert , Aravindh Mahendran

The Segment Anything Model (SAM) has demonstrated impressive generalization in prompt-based segmentation. Yet, the potential of semantic text prompts remains underexplored compared to traditional spatial prompts like points and boxes. This…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Shayan Jalilian , Abdul Bais

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Hanning Chen , Yang Ni , Wenjun Huang , Yezi Liu , SungHeon Jeong , Fei Wen , Nathaniel Bastian , Hugo Latapie , Mohsen Imani

The reliance on large labeled datasets presents a significant challenge in medical image segmentation. Few-shot learning offers a potential solution, but existing methods often still require substantial training data. This paper proposes a…

Image and Video Processing · Electrical Eng. & Systems 2025-03-10 Haiyue Zu , Jun Ge , Heting Xiao , Jile Xie , Zhangzhe Zhou , Yifan Meng , Jiayi Ni , Junjie Niu , Linlin Zhang , Li Ni , Huilin Yang

We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation that casts the task as multi-view 2D mask prediction. Given a textureless object, we render normal and point maps from predefined viewpoints and accept simple 2D…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Ken Deng , Yunhan Yang , Jingxiang Sun , Xihui Liu , Yebin Liu , Ding Liang , Yan-Pei Cao

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Chaoning Zhang , Dongshen Han , Sheng Zheng , Jinwoo Choi , Tae-Ho Kim , Choong Seon Hong

Surgical video segmentation is a critical task in computer-assisted surgery, essential for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has demonstrated remarkable advancements in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Ming Yin , Fu Wang , Xujiong Ye , Yanda Meng , Zeyu Fu