Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
- URL: http://arxiv.org/abs/2412.01240v1
- Date: Mon, 02 Dec 2024 08:03:56 GMT
- Title: Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
- Authors: Xiaoqi Zhao, Youwei Pang, Shijie Chang, Yuan Zhao, Lihe Zhang, Huchuan Lu, Jinsong Ouyang, Georges El Fakhri, Xiaofeng Liu,
- Abstract summary: The foundational model SAM has influenced multiple fields within computer vision, and its upgraded version, SAM 2, enhances capabilities in video segmentation.
While SAMs have demonstrated excellent performance in segmenting context-independent concepts like people, cars, and roads, they overlook more challenging context-dependent (CD) concepts, such as visual saliency, camouflage, product defects, and medical lesions.
We conduct a thorough quantitative evaluation of SAMs on 11 CD concepts across 2D and 3D images and videos in various visual modalities within natural, medical, and industrial scenes.
- Score: 63.966251473172036
- License:
- Abstract: As a foundational model, SAM has significantly influenced multiple fields within computer vision, and its upgraded version, SAM 2, enhances capabilities in video segmentation, poised to make a substantial impact once again. While SAMs (SAM and SAM 2) have demonstrated excellent performance in segmenting context-independent concepts like people, cars, and roads, they overlook more challenging context-dependent (CD) concepts, such as visual saliency, camouflage, product defects, and medical lesions. CD concepts rely heavily on global and local contextual information, making them susceptible to shifts in different contexts, which requires strong discriminative capabilities from the model. The lack of comprehensive evaluation of SAMs limits understanding of their performance boundaries, which may hinder the design of future models. In this paper, we conduct a thorough quantitative evaluation of SAMs on 11 CD concepts across 2D and 3D images and videos in various visual modalities within natural, medical, and industrial scenes. We develop a unified evaluation framework for SAM and SAM 2 that supports manual, automatic, and intermediate self-prompting, aided by our specific prompt generation and interaction strategies. We further explore the potential of SAM 2 for in-context learning and introduce prompt robustness testing to simulate real-world imperfect prompts. Finally, we analyze the benefits and limitations of SAMs in understanding CD concepts and discuss their future development in segmentation tasks. This work aims to provide valuable insights to guide future research in both context-independent and context-dependent concepts segmentation, potentially informing the development of the next version - SAM 3.
Related papers
- Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2 [10.751277821864916]
Report reveals a decline in SAM2's ability to perceive different objects in images without prompts in its auto mode.
Specifically, we employ the challenging task of camouflaged object detection to assess this performance decrease.
arXiv Detail & Related papers (2024-07-31T13:32:10Z) - Segment Anything for Videos: A Systematic Survey [52.28931543292431]
The recent wave of foundation models has witnessed tremendous success in computer vision (CV) and beyond.
The segment anything model (SAM) has sparked a passion for exploring task-agnostic visual foundation models.
This work conducts a systematic review on SAM for videos in the era of foundation models.
arXiv Detail & Related papers (2024-07-31T02:24:53Z) - AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning [61.666973416903005]
Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts.
We propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context.
arXiv Detail & Related papers (2024-06-01T16:21:39Z) - Boosting Segment Anything Model Towards Open-Vocabulary Learning [69.24734826209367]
Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model.
Despite SAM finding applications and adaptations in various domains, its primary limitation lies in the inability to grasp object semantics.
We present Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework.
arXiv Detail & Related papers (2023-12-06T17:19:00Z) - On the Robustness of Segment Anything [46.669794757467166]
We aim to study the testing-time robustness of SAM under adversarial scenarios and common corruptions.
We find that SAM exhibits remarkable robustness against various corruptions, except for blur-related corruption.
arXiv Detail & Related papers (2023-05-25T16:28:30Z) - A Comprehensive Survey on Segment Anything Model for Vision and Beyond [7.920790211915402]
It is urgent to design a general class of models, which we term foundation models, trained on broad data.
The recently proposed segment anything model (SAM) has made significant progress in breaking the boundaries of segmentation.
This paper introduces the background and terminology for foundation models including SAM, as well as state-of-the-art methods contemporaneous with SAM.
arXiv Detail & Related papers (2023-05-14T16:23:22Z) - A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering [49.732628643634975]
The Segment Anything Model (SAM), developed by Meta AI Research, offers a robust framework for image and video segmentation.
This survey provides a comprehensive exploration of the SAM family, including SAM and SAM 2, highlighting their advancements in granularity and contextual understanding.
arXiv Detail & Related papers (2023-05-12T07:21:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.