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

arXiv: https://arxiv.org/abs/2412.01240 · HTML: https://mlsanity.com/paper/2412.01240/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 101 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 30 of 68)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images](https://mlsanity.com/paper/1612.00799/) (2016)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images](https://mlsanity.com/paper/2004.14133/) (2020)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching](https://mlsanity.com/paper/2305.13310/) (2023)
- [Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications](https://mlsanity.com/paper/2304.05750/) (2023)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Global Context-Aware Progressive Aggregation Network for Salient Object Detection](https://mlsanity.com/paper/2003.00651/) (2020)

## Built on by (most cited first, 9 of 9)

- [SAM2 for Image and Video Segmentation: A Comprehensive Survey](https://mlsanity.com/paper/2503.12781/) (2025)
- [TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation](https://mlsanity.com/paper/2604.00684/) (2026)
- [DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance](https://mlsanity.com/paper/2606.08906/) (2026)
- [Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation](https://mlsanity.com/paper/2504.09601/) (2025)
- [SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection](https://mlsanity.com/paper/2503.03942/) (2025)
- [The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation](https://mlsanity.com/paper/2512.06032/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [Leveraging GenAI for Segmenting and Labeling Centuries-old Technical Documents](https://mlsanity.com/paper/2603.00147/) (2026)
- [ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning](https://mlsanity.com/paper/2605.20385/) (2026)

## Abstract (arXiv)

As large-scale foundation models trained on billions of image--mask pairs covering a vast diversity of scenes, objects, and contexts, SAM and its upgraded version, SAM~2, have significantly influenced multiple fields within computer vision. Leveraging such unprecedented data diversity, they exhibit strong open-world segmentation capabilities, with SAM~2 further enhancing these capabilities to support high-quality video segmentation. 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, industrial 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 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.