Cover Image

SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Yiran, Zhou, Qianyu, Lu, Xuequan, Shao, Zhiwen, Ma, Lizhuang
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
by: Song, Yiran, et al.
Published: (2024)

Multi-scale Contrastive Adaptor Learning for Segmenting Anything in Underperformed Scenes
by: Zhou, Ke, et al.
Published: (2024)

Source-Free Test-Time Adaptation For Online Surface-Defect Detection
by: Song, Yiran, et al.
Published: (2024)

MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution
by: Shao, Zhiwen, et al.
Published: (2025)

Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
by: Wu, Junde, et al.
Published: (2023)

MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical Maps
by: Xia, Xue, et al.
Published: (2024)

UV-SAM: Adapting Segment Anything Model for Urban Village Identification
by: Zhang, Xin, et al.
Published: (2024)

Test-Time Domain Generalization for Face Anti-Spoofing
by: Zhou, Qianyu, et al.
Published: (2024)

SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything
by: Ji, Ge-Peng, et al.
Published: (2023)

PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification
by: Yang, Hao, et al.
Published: (2025)

DGMamba: Domain Generalization via Generalized State Space Model
by: Long, Shaocong, et al.
Published: (2024)

PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model
by: Yang, Hao, et al.
Published: (2024)

Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts
by: Xie, Enze, et al.
Published: (2024)

Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models
by: Zhou, Fengfan, et al.
Published: (2024)

Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation
by: Liu, Fengqi, et al.
Published: (2024)

RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
by: Li, Yonglin, et al.
Published: (2023)

Rethinking Impersonation and Dodging Attacks on Face Recognition Systems
by: Zhou, Fengfan, et al.
Published: (2024)

CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
by: Xiao, Aoran, et al.
Published: (2024)

Memorizing SAM: 3D Medical Segment Anything Model with Memorizing Transformer
by: Shao, Xinyuan, et al.
Published: (2024)

StyleRWKV: High-Quality and High-Efficiency Style Transfer with RWKV-like Architecture
by: Dai, Miaomiao, et al.
Published: (2024)

Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2
by: Wang, Zhiting, et al.
Published: (2024)

SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes
by: Wang, Yuji, et al.
Published: (2025)

SAM3-UNet: Simplified Adaptation of Segment Anything Model 3
by: Xiong, Xinyu, et al.
Published: (2025)

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding
by: Jiang, Jincen, et al.
Published: (2024)

SAM3-I: Segment Anything with Instructions
by: Li, Jingjing, et al.
Published: (2025)

SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
by: Chen, Tianrun, et al.
Published: (2024)

Adapting Segment Anything Model for Unseen Object Instance Segmentation
by: Cao, Rui, et al.
Published: (2024)

FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptation
by: Forni, Bernardo, et al.
Published: (2025)

From SAM to SAM 2: Exploring Improvements in Meta's Segment Anything Model
by: Geetha, Athulya Sundaresan, et al.
Published: (2024)

I-MedSAM: Implicit Medical Image Segmentation with Segment Anything
by: Wei, Xiaobao, et al.
Published: (2023)

Learning Adaptive Node Selection with External Attention for Human Interaction Recognition
by: Pang, Chen, et al.
Published: (2025)

ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation
by: Pu, Xinyang, et al.
Published: (2024)

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
by: Ye, Maoyuan, et al.
Published: (2024)

CurvNet: Latent Contour Representation and Iterative Data Engine for Curvature Angle Estimation
by: Shao, Zhiwen, et al.
Published: (2024)

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
by: Huang, Duojun, et al.
Published: (2024)

PaveSAM Segment Anything for Pavement Distress
by: Owor, Neema Jakisa, et al.
Published: (2024)

SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
by: Han, Dongshen, et al.
Published: (2023)

DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
by: Qi, Mengshi, et al.
Published: (2025)

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
by: Zhao, Xiaoqi, et al.
Published: (2024)

TinySAM: Pushing the Envelope for Efficient Segment Anything Model
by: Shu, Han, et al.
Published: (2023)