Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection
Not on the map. Why?
Abstract (arXiv)
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of learning discriminative representation in OOD detection. However, for its limited vision, merely focusing on instance-level relationship between augmented samples, it lacks attention to the relationship between samples with same semantics. Based on the classic contrastive learning, we propose Cluster-aware Contrastive Learning (CCL) framework for unsupervised OOD detection, which considers both instance-level and semantic-level information. Specifically, we study a cooperation strategy of clustering and contrastive learning to effectively extract the latent semantics and design a cluster-aware contrastive loss function to enhance OOD discriminative ability. The loss function can simultaneously pay attention to the global and local relationships by treating both the cluster centers and the samples belonging to the same cluster as positive samples. We conducted sufficient experiments to verify the effectiveness of our framework and the model achieves significant improvement on various image benchmarks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 30 references that are in the map. First posted on arXiv 6 Feb 2023.
Builds on
27 of 30 references.
References · 27
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2020Supervised Contrastive Learningcited by 2,803
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
- 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
- 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
- 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
15 more
- 2020Contrastive Clusteringcited by 264
- 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
- 2020Classification-Based Anomaly Detection for General Datacited by 210
- 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
- 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
- 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
- 2021Supporting Clustering with Contrastive Learningcited by 90
- 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
- 2021Graph Contrastive Clusteringcited by 61
- 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
- 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
- 2021Masked Contrastive Learning for Anomaly Detectioncited by 23
- 2020Clustering based Contrastive Learning for Improving Face Representationscited by 21
- 2022Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasetscited by 6
- 2022Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Spacecited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.