Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to distance-based OOD detection, where testing samples are detected as OOD if they are relatively far away from the centroids or prototypes of in-distribution (ID) classes. However, prior methods directly take off-the-shelf contrastive losses that suffice for classifying ID samples, but are not optimally designed when test inputs contain OOD samples. In this work, we propose CIDER, a novel representation learning framework that exploits hyperspherical embeddings for OOD detection. CIDER jointly optimizes two losses to promote strong ID-OOD separability: a dispersion loss that promotes large angular distances among different class prototypes, and a compactness loss that encourages samples to be close to their class prototypes. We analyze and establish the unexplored relationship between OOD detection performance and the embedding properties in the hyperspherical space, and demonstrate the importance of dispersion and compactness. CIDER establishes superior performance, outperforming the latest rival by 19.36% in FPR95. Code is available at https://github.com/deeplearning-wisc/cider.
MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition
Institute of Biosciences, Humanities and Exact Sciences（生物科学与人文与精确科学研究所）；São Paulo State University（圣保罗州大学）；São José do Rio Preto, Brazil（巴西圣保罗州萨o Jos6 do Rio Preto）
Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
Department of Information Technology, Uppsala University, Uppsala, Sweden（瑞典乌普萨拉大学信息科技系）；Science for Life Laboratory, Uppsala University, Uppsala, Sweden（瑞典乌普萨拉大学生命科学实验室）
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
Arizona State University（亚利桑那州立大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
在本文中，我们开发了一个Wasserstein自动编码器（WAE）与超球先验多模数据在惯性约束聚变的应用。与典型的超球面生成模型不同，它需要从von Mis Fisher等分布中进行计算效率低下的采样，我们从正态分布中采样，然后在生成器之前进行投影层。最后，为了确定生成的样本的有效性，我们利用数据集中模态之间的已知关系作为科学约束，并研究所提出的模型的不同属性。
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
Sun Yat-sen University（中山大学）；South China Agricultural University（华南农业大学）；University of Electronic Science and Technology of China（电子科技大学）；Guilin University of Electronic Technology（桂林电子科技大学）
