Divide-and-conquer for enhancing unlabeled learning, stability, and plasticity in semi-supervised continual learningAug 12, 2025·Yue Duan,Taicai Chen,Lei QiYinghuan Shi· 0 min read Cite URLTypeConference paperPublicationProceedings of the IEEE/CVF International Conference on Computer VisionLast updated on Aug 12, 2025AuthorsYinghuan ShiNanjing University← Correspondence as video: test-time adaption on SAM2 for reference segmentation in the wild Aug 12, 2025Make your training flexible: towards deployment-efficient video models Aug 12, 2025 →
