TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
- CoCo-SAM3: Harnessing Concept Conflict in Open-Vocabulary Semantic Segmentation
- SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
- Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3
- Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
- VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models