Learning with Mixture of Prototypes for Out-of-Distribution Detection
Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection methods have emerged with enhanced deep representation learning. They identify unseen OOD samples by measuring their distances from ID class centroids or prototypes. However, existing approaches learn the representation relying on oversimplified data assumptions, e.g, modeling ID data of each class with one centroid class prototype or using loss functions not designed for OOD detection, which overlook the natural diversities within the data. Naively enforcing data samples of each class to be compact around only one prototype leads to inadequate modeling of realistic data and limited performance. To tackle these issues, we propose PrototypicAl Learning with a Mixture of prototypes (PALM) which models each class with multiple prototypes to capture the sample diversities, and learns more faithful and compact samples embeddings to enhance OOD detection. Our method automatically identifies and dynamically updates prototypes, assigning each sample to a subset of prototypes via reciprocal neighbor soft assignment weights. PALM optimizes a maximum likelihood estimation (MLE) loss to encourage the sample embeddings to be compact around the associated prototypes, as well as a contrastive loss on all prototypes to enhance intra-class compactness and inter-class discrimination at the prototype level. Moreover, the automatic estimation of prototypes enables our approach to be extended to the challenging OOD detection task with unlabelled ID data. Extensive experiments demonstrate the superiority of PALM, achieving state-of-the-art average AUROC performance of 93.82 on the challenging CIFAR-100 benchmark. Code is available at https://github.com/jeff024/PALM.
Code (1)
Tasks
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Infinite Mixture Prototypes for Few-Shot Learning
We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing …
ClusteringFew-Shot LearningMixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Prototypical-part methods, e.g., ProtoPNet, enhance interpretability in image recognition by linking predictions to training prototypes, thereby offering intuitive insights into their decision-making. Existing methods, w…
Explainable Artificial Intelligence (XAI)image-classificationImage ClassificationInterpretable Machine Learning+1Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational mod…
Decision MakingOut-of-Distribution DetectionOut of Distribution (OOD) DetectionMixture of von Mises-Fisher distribution with sparse prototypes
Mixtures of von Mises-Fisher distributions can be used to cluster data on the unit hypersphere. This is particularly adapted for high-dimensional directional data such as texts. We propose in this article to estimate a v…
ClusteringOn Partial Prototype Collapse in the DINO Family of Self-Supervised Methods
A prominent self-supervised learning paradigm is to model the representations as clusters, or more generally as a mixture model. Learning to map the data samples to compact representations and fitting the mixture model s…
Self-Supervised Learning