Cover Image

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Junwei, Darrell, Trevor, Wang, XuDong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Segment Anything without Supervision
by: Wang, XuDong, et al.
Published: (2024)

Reconstruction Alignment Improves Unified Multimodal Models
by: Xie, Ji, et al.
Published: (2025)

Visual Lexicon: Rich Image Features in Language Space
by: Wang, XuDong, et al.
Published: (2024)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
by: Qin, Yiming, et al.
Published: (2025)

SegLLM: Multi-round Reasoning Segmentation
by: Wang, XuDong, et al.
Published: (2024)

X-SAM: From Segment Anything to Any Segmentation
by: Wang, Hao, et al.
Published: (2025)

Compress Any Segment Anything Model (SAM)
by: Fan, Juntong, et al.
Published: (2025)

Tracking and Segmenting Anything in Any Modality
by: Zhang, Tianlu, et al.
Published: (2025)

TULIP: Towards Unified Language-Image Pretraining
by: Tang, Zineng, et al.
Published: (2025)

BiSeg-SAM: Weakly-Supervised Post-Processing Framework for Boosting Binary Segmentation in Segment Anything Models
by: Su, Encheng, et al.
Published: (2025)

Depth Anything at Any Condition
by: Sun, Boyuan, et al.
Published: (2025)

SAM 2: Segment Anything in Images and Videos
by: Ravi, Nikhila, et al.
Published: (2024)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
by: Huang, Brandon, et al.
Published: (2024)

Red-Teaming Segment Anything Model
by: Jankowski, Krzysztof, et al.
Published: (2024)

ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting
by: Bhattarai, Ananta R., et al.
Published: (2025)

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
by: Zohar, Orr, et al.
Published: (2024)

Hidden in plain sight: VLMs overlook their visual representations
by: Fu, Stephanie, et al.
Published: (2025)

DeiSAM: Segment Anything with Deictic Prompting
by: Shindo, Hikaru, et al.
Published: (2024)

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
by: Franco, Luca, et al.
Published: (2023)

Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Images
by: Liu, Qingyuan, et al.
Published: (2024)

Describe Anything: Detailed Localized Image and Video Captioning
by: Lian, Long, et al.
Published: (2025)

Describe Anything Anywhere At Any Moment
by: Gorlo, Nicolas, et al.
Published: (2025)

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
by: Zhu, Lianghui, et al.
Published: (2024)

LENS: Learning to Segment Anything with Unified Reinforced Reasoning
by: Zhu, Lianghui, et al.
Published: (2025)

Self-Evaluation Unlocks Any-Step Text-to-Image Generation
by: Yu, Xin, et al.
Published: (2025)

Count Anything at Any Granularity
by: Liu, Chang, et al.
Published: (2026)

Composition Vision-Language Understanding via Segment and Depth Anything Model
by: Huo, Mingxiao, et al.
Published: (2024)

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound
by: Huang, Yuhao, et al.
Published: (2025)

REOrdering Patches Improves Vision Models
by: Kutscher, Declan, et al.
Published: (2025)

InstanceDiffusion: Instance-level Control for Image Generation
by: Wang, Xudong, et al.
Published: (2024)

Lifting Embodied World Models for Planning and Control
by: Wang, Alex N., et al.
Published: (2026)

Self-Supervised Learning of Color Constancy
by: Ernst, Markus R., et al.
Published: (2024)

Blockwise Self-Supervised Learning at Scale
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2023)

EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss
by: Zhang, Zhuoyang, et al.
Published: (2024)

SAM 2++: Tracking Anything at Any Granularity
by: Zhang, Jiaming, et al.
Published: (2025)

Compositional Chain-of-Thought Prompting for Large Multimodal Models
by: Mitra, Chancharik, et al.
Published: (2023)

On Pretraining Data Diversity for Self-Supervised Learning
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

Rethinking The Uniformity Metric in Self-Supervised Learning
by: Fang, Xianghong, et al.
Published: (2024)

Matrix Information Theory for Self-Supervised Learning
by: Zhang, Yifan, et al.
Published: (2023)

SAM 3: Segment Anything with Concepts
by: Carion, Nicolas, et al.
Published: (2025)