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.
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...
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
arXiv:2608.29917v1 Announce Type: new Abstract: Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes...
Prompt-driven vision-language models (VLMs) hold immense promise for accelerating dense remote sensing (RS) annotation, but static models suffer from severe performance degradation when deployed on novel scenes, unseen categories, or visually confusing backgrounds. Moreover, existing unified paradigms primarily rely on intra-image specific prompts, lacking flexible task routing to adapt to multi-intent operational workflows.
The paper introduces DCR‑SAM, a framework that adapts the Segment Anything Model 3 (SAM3) for multi‑class semantic segmentation. By decoupling cross‑modal interactions, aligning textual concepts with visual representations, and adding a dense competition head and learnable background token, DCR‑SAM reduces inference latency, mitigates semantic misclassifications, and suppresses overlapping predictions. Experiments show 2.3%–10.7% performance gains, a 33× speedup over native SAM3, and strong robustness across benchmarks.
PANORAMA introduces a new panoptic grounded captioning framework that jointly generates detailed image captions and associates each phrase with precise pixel-level masks. The authors create PanoCaps, a human‑annotated benchmark with dense captions and near‑complete pixel coverage, and propose a phrase‑mask matching protocol with a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations, learns to select appropriate masks, and achieves state‑of‑the‑art grounding performance on PanoCaps and other pixel‑level tasks.
Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes the object within a target image, the latter retr...
arXiv:2501.04001v4 Announce Type: replace Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image ca...
arXiv:2607.12896v3 Announce Type: replace Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fr...
The Segment Anything Model 3 (SAM3) has achieved significant progress in Promptable Concept Segmentation (PCS) by processing short noun phrases to generate segmentation masks with unique instance iden...
arXiv:2604. 20329v3 Announce Type: replace-cross Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining.