xiongxyowo的个人简介
Research Interest
- Dataset Perspective:各类二分割,包括但不限于息肉分割(Polyp Segmentation),乳腺钼靶分割(Mammogram Segmentation),显著性检测(Salient Object Detection),伪装目标检测(Camouflage Object Detection),视频分割(Video Segmentation)
- Method Perspective:不完美标注下的学习,包括主动学习(Active Learning),半监督学习(Semi-supervised Learning),图像翻译应用(Image Translation Applications),领域自适应(Domain Adaptation),类增量学习(Class-Incremental Learning),弱监督学习(Weakly-supervised Learning)
- Emerging Fields: Diffusion生成模型的应用,图像文本多模态(Image-Text Representation Learning),大型分割模型(Segment Anything Model)
Publications
- [CVPR 24] AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
- [ISBI 24] Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations
- [ISBI 24] Annotation-Efficient Polyp Segmentation via Active Learning
- [ISBI 24] Source-Free Semi-Supervised Domain Adaptation for Tuberculosis Recognition
- [ISBI 24] BCFNet: Boundary-guided Semantic Cross Fusion for Polyp Segmentation
- [SPL 24] HybridVPS: Hybrid-supervised Video Polyp Segmentation Under Low-Cost Labels
- [MLMI 23] Mammo-SAM: Adapting Foundation Segment Anything Model for Automatic Breast Mass Segmentation in Whole Mammograms
- [IJCAI 23] Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer
- [ISBI 23] Unpaired Image-to-Image Translation based Domain Adaptation for Polyp Segmentation
Advertisement
欢迎感兴趣的同学扫下方二维码一起讨论交流有关学术问题: