{"ID":2888252,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23307","arxiv_id":"2507.23307","title":"ST-SAM: SAM-Driven Self-Training Framework for Semi-Supervised Camouflaged Object Detection","abstract":"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.","short_abstract":"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 super...","url_abs":"https://arxiv.org/abs/2507.23307","url_pdf":"https://arxiv.org/pdf/2507.23307v1","authors":"[\"Xihang Hu\",\"Fuming Sun\",\"Jiazhe Liu\",\"Feilong Xu\",\"Xiaoli Zhang\"]","published":"2025-07-31T07:41:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611521,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888252,"paper_url":"https://arxiv.org/abs/2507.23307","paper_title":"ST-SAM: SAM-Driven Self-Training Framework for Semi-Supervised Camouflaged Object Detection","repo_url":"https://github.com/hu-xh/ST-SAM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}