生物通

HierAnom-Path: 基于层次化基础模型自适应的组织病理学零样本罕见癌症检测

罕见癌症总体上占所有恶性肿瘤的20%–25%，但在公开可用的存档中，每个亚型标注的全切片图像（WSI）少于50张，这使得监督深度学习不可行。研究人员提出了HierAnom-Path，据研究人员所知，这是第一个在千兆像素组织病理学WSI中进行零样本罕见癌症异常检 罕见癌症总体上占所有恶性肿瘤的20%–25%，但在公开可用的存档中，每个亚型标注的全切片图像（WSI）少于50张，这使得监督深度学习不可行 ...
GitHub

Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection

PyTorch implementation for CVPR2023 paper, Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection. python main.py --flow_arch ...
GitHub

Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation

Xiaoyang Wang, Bingfeng Zhang, Limin Yu, and Jimin Xiao. In CVPR 2023. Abstract: Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions ...