DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation

[2506.23104] DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2506.23104 (cs) [Submitted on 29 Jun 2025 ( v1 ), last revised 14 Apr 2026 (this version, v2)] Title: DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation Authors: Jihun Kim , Hoyong Kwon , Hyeokjun Kweon , Wooseong Jeong , Kuk-Jin Yoon View a PDF of the paper titled DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation, by Jihun Kim and 4 other authors View PDF HTML (experimental) Abstract: Interactive segmentation (IS) allows users to iteratively refine object boundaries with minimal cues, such as positive and negative clicks. While the Segment Anything Model (SAM) has garnered attention in the IS community for its promptable segmentation capabilities, it often struggles in specialized domains or when handling complex scenarios (e.g., camouflaged or multi-part objects). To overcome these challenges, we propose DC-TTA, a novel test-time adaptation (TTA) framework that adapts SAM on a per-sample basis by leveraging user interactions as supervision. Instead of forcing a single model to incorporate all user clicks at once, DC-TTA partitions the clicks into more coherent subsets, each processed independently via TTA with a separated model. This Divide-and-Conquer strategy reduces conflicts among diverse cues and enables more localized updates. Finally, we merge the adapted models to form a unified predictor that integrates the specialized knowledge from each subset. Experimental results across various benchmarks demonstrate that DC-TTA significantly outperforms SAM's zero-shot results and conventional TTA methods, effectively handling complex tasks such as camouflaged object segmentation with fewer interactions and improved accuracy. Comments: accepted at ICCV 2025 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2506.23104 [cs.CV] (or arXiv:2506.23104v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2506.23104 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jihun Kim [ view email ] [v1] Sun, 29 Jun 2025 06:10:00 UTC (12,796 KB) [v2] Tue, 14 Apr 2026 08:12:06 UTC (12,796 KB) Full-text links: Access Paper: View a PDF of the paper titled DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation, by Jihun Kim and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V#622585
• MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios#617829
• MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios#617329
• Less is More: Encoder-only Audio-Visual Segmentation#1077050
• RESAMPL-UDA: Leveraging foundation models for unsupervised domain adaptation in biomedical images#922978