# Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects

arXiv: https://arxiv.org/abs/2312.07374 · HTML: https://mlsanity.com/paper/2312.07374/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization](https://mlsanity.com/paper/2112.00463/) (2021)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [Weakly-Supervised Salient Object Detection via Scribble Annotations](https://mlsanity.com/paper/2003.07685/) (2020)
- [A Closer Look at the Explainability of Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2304.05653/) (2023)
- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions](https://mlsanity.com/paper/2303.06594/) (2023)
- [SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything](https://mlsanity.com/paper/2304.06022/) (2023)
- [Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence](https://mlsanity.com/paper/2012.04404/) (2020)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)

## Built on by (most cited first, 30 of 40)

- [Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning](https://mlsanity.com/paper/2506.22624/) (2025)
- [A Survey of Camouflaged Object Detection and Beyond](https://mlsanity.com/paper/2408.14562/) (2024)
- [SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2505.22596/) (2025)
- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation](https://mlsanity.com/paper/2408.15205/) (2024)
- [CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection](https://mlsanity.com/paper/2408.08050/) (2024)
- [CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation](https://mlsanity.com/paper/2506.23121/) (2025)
- [Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement](https://mlsanity.com/paper/2508.15027/) (2025)
- [MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation](https://mlsanity.com/paper/2503.06700/) (2025)
- [MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval](https://mlsanity.com/paper/2406.17880/) (2024)
- [FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2409.03525/) (2024)
- [AoP-SAM: Automation of Prompts for Efficient Segmentation](https://mlsanity.com/paper/2505.11980/) (2025)
- [Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategy](https://mlsanity.com/paper/2408.12086/) (2024)
- [Deep Learning in Concealed Dense Prediction](https://mlsanity.com/paper/2504.10979/) (2025)
- [SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation](https://mlsanity.com/paper/2511.18136/) (2025)
- [Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection](https://mlsanity.com/paper/2510.18437/) (2025)
- [EchoONE: Segmenting Multiple echocardiography Planes in One Model](https://mlsanity.com/paper/2412.02993/) (2024)
- [Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking](https://mlsanity.com/paper/2503.16538/) (2025)
- [Segment Concealed Objects with Incomplete Supervision](https://mlsanity.com/paper/2506.08955/) (2025)
- [Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection](https://mlsanity.com/paper/2410.03987/) (2024)
- [Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations](https://mlsanity.com/paper/2410.16953/) (2024)
- [INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation](https://mlsanity.com/paper/2501.18753/) (2025)
- [Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation](https://mlsanity.com/paper/2506.06818/) (2025)
- [Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges](https://mlsanity.com/paper/2507.09562/) (2025)
- [SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection](https://mlsanity.com/paper/2508.17843/) (2025)
- [MCOD: The First Challenging Benchmark for Multispectral Camouflaged Object Detection](https://mlsanity.com/paper/2509.15753/) (2025)
- [Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation](https://mlsanity.com/paper/2602.19944/) (2026)
- [Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2503.21140/) (2025)
- [Learning Accurate Segmentation Purely from Self-Supervision](https://mlsanity.com/paper/2602.23759/) (2026)
- [ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation](https://mlsanity.com/paper/2606.20161/) (2026)

## Abstract (arXiv)

Camouflaged object detection (COD) approaches heavily rely on pixel-level annotated datasets. Weakly-supervised COD (WSCOD) approaches use sparse annotations like scribbles or points to reduce annotation effort, but this can lead to decreased accuracy. The Segment Anything Model (SAM) shows remarkable segmentation ability with sparse prompts like points. However, manual prompt is not always feasible, as it may not be accessible in real-world application. Additionally, it only provides localization information instead of semantic one, which can intrinsically cause ambiguity in interpreting the targets. In this work, we aim to eliminate the need for manual prompt. The key idea is to employ Cross-modal Chains of Thought Prompting (CCTP) to reason visual prompts using the semantic information given by a generic text prompt. To that end, we introduce a test-time adaptation per-instance mechanism called Generalizable SAM (GenSAM) to automatically enerate and optimize visual prompts the generic task prompt for WSCOD. In particular, CCTP maps a single generic text prompt onto image-specific consensus foreground and background heatmaps using vision-language models, acquiring reliable visual prompts. Moreover, to test-time adapt the visual prompts, we further propose Progressive Mask Generation (PMG) to iteratively reweight the input image, guiding the model to focus on the targets in a coarse-to-fine manner. Crucially, all network parameters are fixed, avoiding the need for additional training. Experiments demonstrate the superiority of GenSAM. Experiments on three benchmarks demonstrate that GenSAM outperforms point supervision approaches and achieves comparable results to scribble supervision ones, solely relying on general task descriptions as prompts. our codes is in: https://lwpyh.github.io/GenSAM/.