ASAP (Attention Sink Anchored Pruning) is a training‑free framework designed to reduce the computational burden of Vision Transformers by addressing the attention sink problem. It models ViT information flow as a Lazy Random Walk, identifies the sink as a dominant probability accumulator, and uses diffusion distance to partition tokens via Radial Diffusion Clustering. The method then compresses background redundancy through Transition Weight Pooling, achieving up to 48% throughput acceleration while maintaining or improving accuracy across image, video, and vision‑language tasks.
By Jaehyuk Lee, Hanyoung Kim, Yanggee Kim, Donghun Lee
Text-to-image diffusion transformers learn about objects and scenes by learning to generate them, making them strong candidates for training-free zero-shot open-vocabulary semantic segmentation. State-of-the-art attribution methods score each pixel independently, comparing its features against a fixed text-derived class representation, whether as an output-space similarity or as a cross-attention weight.
arXiv:2503. 15639v2 Announce Type: replace-cross Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios.
By Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal, Cheng-Lin Liu
FoRIS is a training‑free in‑context segmentation framework that refines foreground masks through a coarse‑to‑fine process. It operates in three stages—Foreground Purification, Localization, and Consolidation—to suppress background noise, pinpoint target regions, and reconstruct complete foreground structures. The method achieves state‑of‑the‑art performance, improving mIoU by 4.5 and 4.8 points in 1‑shot and 5‑shot settings respectively.
By Ming Hu, Jianfu Yin, Mingyu Dou, Miaomiao Zhang, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang
SetCon reformulates open-ended referring segmentation as set-level concept prediction, using LVLM-generated natural-language concepts instead of segmentation-specific tokens. It employs a hierarchical semantic decomposition that first predicts a shared set-level concept and then refines it into fine-grained concept groups aligned with target subsets. The method, supported by a two-stage annotation pipeline adding hierarchical semantic supervision, achieves state-of-the-art results on multiple image and video benchmarks, with performance gains increasing as the number of referred targets grows.
By Zhixiong Zhang, Yizhuo Li, Shuangrui Ding, Yuhang Zang, Shengyuan Ding, Long Xing, Yibin Wang, Qiaosheng Zhang, Jiaqi Wang
arXiv:2502. 06818v4 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS).
By Jingyun Wang, Cilin Yan, Guoliang Kang
UnSAMv2 is a self‑supervised extension of the Segment Anything Model that can segment objects at any granularity without human annotations. It discovers mask‑granularity pairs and introduces a granularity control embedding for continuous scale adjustment, requiring only 6K unlabeled images and 0.02% extra parameters. The model outperforms SAM/SAM‑2 across 11+ benchmarks, improving metrics such as 1‑IoU from 58.0 to 73.1 and achieving state‑of‑the‑art performance on language‑guided segmentation.
By Junwei Yu, Trevor Darrell, XuDong Wang
The paper introduces Text-to-Seed (T2S), a training‑free framework for open‑vocabulary semantic segmentation that repurposes Stable Diffusion to generate attention‑based seed points from text queries. These sparse seeds serve as point prompts for the Segment Anything Model (SAM), enabling reliable region expansion without relying on inaccurate coarse masks. T2S achieves strong performance on standard OVSS benchmarks using only the text‑to‑region correspondence of diffusion models and no task‑specific training or extra annotations.
By Kumju Jo, Heesun Jung, Sungyong Baik
arXiv:2609.39785v1 Announce Type: new
Abstract: The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised...
By Weijian Jian, Xiaoyue Zhang, Bin Xiao, Chunyu Xie, Yixiao He, Yutao Liu, Dawei Leng, Yuhui Yin
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
By Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang
arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.
By Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong
Diffusion-based data augmentation has emerged as a powerful strategy for addressing data-scarce image classification. Recent pipelines typically adapt a pretrained text-to-image diffusion model to a l...