mlsanityData to 7 Oct 2026

Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2

arXiv 2407.21596 ↗First posted 31 Jul 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its application to video, Meta further develops Segment Anything Model 2 (SAM2), a unified model capable of both video and image segmentation. SAM2 shows notable improvements over its predecessor in terms of applicable domains, promptable segmentation accuracy, and running speed. However, this report reveals a decline in SAM2's ability to perceive different objects in images without prompts in its auto mode, compared to SAM. Specifically, we employ the challenging task of camouflaged object detection to assess this performance decrease, hoping to inspire further exploration of the SAM model family by researchers. The results of this paper are provided in urlhttps://github.com/luckybird1994/SAMCOD.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 31 Jul 2024.

Builds on

28 of 39 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Segment Anythingcited by 8,158
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  10. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  11. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
  12. 2021Concealed Object Detectioncited by 212
16 more
  1. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  2. 2021Visual Saliency Transformercited by 175
  3. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  4. 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
  5. 2021Salient Object Detection via Integrity Learningcited by 133
  6. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  7. 2021Mutual Graph Learning for Camouflaged Object Detectioncited by 103
  8. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 99
  9. 2021Context-aware Cross-level Fusion Network for Camouflaged Object Detectioncited by 86
  10. 2022Boundary-Guided Camouflaged Object Detectioncited by 68
  11. 2022Deep Gradient Learning for Efficient Camouflaged Object Detectioncited by 65
  12. 2022Implicit Motion Handling for Video Camouflaged Object Detectioncited by 60
  13. 2021Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Networkcited by 42
  14. 2022Feature Aggregation and Propagation Network for Camouflaged Object Detectioncited by 40
  15. 2022Camouflaged Object Detection via Context-aware Cross-level Fusioncited by 32
  16. 2023Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detectioncited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 1.

12 papers.

  1. 2024When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptationcited by 11
  2. 2025Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2cited by 11
  3. 2024Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenescited by 8
  4. 2025CamSAM2: Segment Anything Accurately in Camouflaged Videoscited by 7
  5. 2024Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentationcited by 5
  6. 2024Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotationscited by 3
  7. 2026Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentationcited by 3
  8. 2025ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detectioncited by 2
  9. 2025C3Net: Context-Contrast Network for Camouflaged Object Detectioncited by 2
  10. 2024When SAM2 Meets Video Shadow and Mirror Detectioncited by 1
  11. 2025SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detectioncited by 0
  12. 2025Promptable Fire Segmentation: Unleashing SAM2's Potential for Real-Time Mobile Deployment with Strategic Bounding Box Guidancecited by 0