paper-with-me

Papers

How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?

2022-03-08 · Yifei Ming, Yiyou Sun, Ousmane Dia, Yixuan Li

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.

📄 PDF Abstract BibTeX arXiv:2203.04450

Code (1)

deeplearning-wisc/cider 공식 구현 pytorch

Tasks

Out-of-Distribution DetectionOut of Distribution (OOD) DetectionRepresentation Learning

Similar Papers 제목 키워드 기반

Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

2026-05-29 · Willian T. Lunardi, Samridha Shrestha, Martin Andreoni arxiv

Out-of-distribution (OOD) detection for time-series data remains comparatively underexplored compared to vision and language, with a limited principled understanding of how supervised time-series representations can be l…

Out-of-Distribution DetectionRepresentation LearningContrastive Learning

Hyperspherical Query Likelihood Models with Word Embeddings

2017-11-01 · IJCNLP 2017 11 · Ryo Masumura, Taichi Asami, Hirokazu Masataki, Kugatsu Sadamitsu 외

This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, …

Information RetrievalLanguage ModelingLanguage ModellingRetrieval+2

Hyperspherical Embedding for Point Cloud Completion

2023-07-11 · CVPR 2023 1 · Junming Zhang, Haomeng Zhang, Ram Vasudevan, Matthew Johnson-Roberson

Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often …

DecoderMulti-Task LearningPoint Cloud Completion

Your Classifier Can Be Secretly a Likelihood-Based OOD Detector

2024-08-09 · Jirayu Burapacheep, Yixuan Li

The ability to detect out-of-distribution (OOD) inputs is critical to guarantee the reliability of classification models deployed in an open environment. A fundamental challenge in OOD detection is that a discriminative …

Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling

2025-07-01 · Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Théo Bontempelli 외 arxiv

This paper introduces von Mises-Fisher exploration (vMF-exp), a scalable method for exploring large action sets in reinforcement learning problems where hyperspherical embedding vectors represent these actions. vMF-exp i…

Reinforcement Learning