Cover Image

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Xiaoqi, Pang, Youwei, Chang, Shijie, Zhao, Yuan, Zhang, Lihe, Yu, Chenyang, Liu, Hanqi, Zuo, Jiaming, Ouyang, Jinsong, Lin, Weisi, Fakhri, Georges El, Lu, Huchuan, Liu, Xiaofeng
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

Power Battery Detection
by: Zhao, Xiaoqi, et al.
Published: (2025)

UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression
by: Zhao, Yuan, et al.
Published: (2025)

Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation
by: Wei, Jia, et al.
Published: (2025)

UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
by: Zhao, Xiaoqi, et al.
Published: (2025)

Open-Vocabulary Camouflaged Object Segmentation
by: Pang, Youwei, et al.
Published: (2023)

Rethinking Evaluation of Infrared Small Target Detection
by: Pang, Youwei, et al.
Published: (2025)

Spider: A Unified Framework for Context-dependent Concept Segmentation
by: Zhao, Xiaoqi, et al.
Published: (2024)

Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
by: Zhao, Xiaoqi, et al.
Published: (2023)

Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM
by: Liu, Xiaofeng, et al.
Published: (2024)

Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation
by: Chang, Shijie, et al.
Published: (2024)

ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning
by: Zhao, Yuan, et al.
Published: (2026)

ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer
by: Pang, Youwei, et al.
Published: (2023)

Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
by: Zhao, Xiaoqi, et al.
Published: (2023)

Towards Diverse Binary Segmentation via A Simple yet General Gated Network
by: Zhao, Xiaoqi, et al.
Published: (2023)

Multi-view Aggregation Network for Dichotomous Image Segmentation
by: Yu, Qian, et al.
Published: (2024)

ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
by: Pang, Youwei, et al.
Published: (2023)

AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
by: Li, Yuchen, et al.
Published: (2024)

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

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

ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts
by: Wang, Xiaoqi, et al.
Published: (2025)

Region-Guided Attack on the Segment Anything Model (SAM)
by: Liu, Xiaoliang, et al.
Published: (2024)

SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptation
by: Fu, Changhong, et al.
Published: (2023)

PromptSAM+: Malware Detection based on Prompt Segment Anything Model
by: Wei, Xingyuan, et al.
Published: (2024)

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

HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation
by: Zhang, Pingping, et al.
Published: (2026)

Towards Large Model Feature Coding
by: Pang, Youwei, et al.
Published: (2026)

MedSAM3: Delving into Segment Anything with Medical Concepts
by: Liu, Anglin, et al.
Published: (2025)

M$^{2}$SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
by: Zhao, Xiaoqi, et al.
Published: (2023)

Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment
by: Lian, Shijie, et al.
Published: (2024)

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

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

The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation
by: Sapkota, Ranjan, et al.
Published: (2025)

ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
by: Zhang, Xike, et al.
Published: (2026)

Unsupervised Adaptation from FDG to PSMA PET/CT for 3D Lesion Detection under Label Shift
by: Liu, Xiaofeng, et al.
Published: (2026)

SAM-OCTA: Prompting Segment-Anything for OCTA Image Segmentation
by: Chen, Xinrun, et al.
Published: (2023)

SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
by: Tang, Zixuan, et al.
Published: (2026)

EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
by: Zhang, Yuxuan, et al.
Published: (2024)

High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Study
by: Chang, Shijie, et al.
Published: (2024)

SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising
by: Zhou, Tao, et al.
Published: (2024)

WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images
by: Liu, Hong, et al.
Published: (2024)