# ST-SAM: SAM-Driven Self-Training Framework for Semi-Supervised Camouflaged Object Detection

arXiv: https://arxiv.org/abs/2507.23307 · HTML: https://mlsanity.com/paper/2507.23307/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [Self-Training: A Survey](https://mlsanity.com/paper/2202.12040/) (2022)
- [SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything](https://mlsanity.com/paper/2304.06022/) (2023)
- [Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects](https://mlsanity.com/paper/2308.03166/) (2023)
- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection](https://mlsanity.com/paper/2408.10760/) (2024)
- [Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection](https://mlsanity.com/paper/2407.12339/) (2024)
- [Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation](https://mlsanity.com/paper/2408.15205/) (2024)
- [Pseudo-label Alignment for Semi-supervised Instance Segmentation](https://mlsanity.com/paper/2308.05359/) (2023)
- [Learning Camouflaged Object Detection from Noisy Pseudo Label](https://mlsanity.com/paper/2407.13157/) (2024)
- [CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection](https://mlsanity.com/paper/2408.08050/) (2024)
- [SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention](https://mlsanity.com/paper/2406.05802/) (2024)
- [Multi-scale Contrastive Adaptor Learning for Segmenting Anything in Underperformed Scenes](https://mlsanity.com/paper/2408.05936/) (2024)

## Built on by (most cited first, 4 of 4)

- [Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark](https://mlsanity.com/paper/2508.04260/) (2025)
- [ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation](https://mlsanity.com/paper/2606.20161/) (2026)
- [Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection](https://mlsanity.com/paper/2604.12380/) (2026)
- [Weakly-Supervised RGB-D Salient Object Detection via SAM-driven Pseudo Annotation and State Space Interaction-based Diffusion](https://mlsanity.com/paper/2607.15041/) (2026)

## Abstract (arXiv)

Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student frameworks suffer from severe prediction bias and error propagation under scarce supervision, while their multi-network architectures incur high computational overhead and limited scalability. To overcome these limitations, we propose ST-SAM, a highly annotation-efficient yet concise framework that breaks away from conventional SSCOD constraints. Specifically, ST-SAM employs Self-Training strategy that dynamically filters and expands high-confidence pseudo-labels to enhance a single-model architecture, thereby fundamentally circumventing inter-model prediction bias. Furthermore, by transforming pseudo-labels into hybrid prompts containing domain-specific knowledge, ST-SAM effectively harnesses the Segment Anything Model's potential for specialized tasks to mitigate error accumulation in self-training. Experiments on COD benchmark datasets demonstrate that ST-SAM achieves state-of-the-art performance with only 1% labeled data, outperforming existing SSCOD methods and even matching fully supervised methods. Remarkably, ST-SAM requires training only a single network, without relying on specific models or loss functions. This work establishes a new paradigm for annotation-efficient SSCOD. Codes will be available at https://github.com/hu-xh/ST-SAM.