WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis
Deep neural networks are susceptible to generating overconfident yet erroneous predictions when presented with data beyond known concepts. This challenge underscores the importance of detecting out-of-distribution (OOD) samples in the open world. In this work, we propose a novel feature-space OOD detection score based on class-specific and class-agnostic information. Specifically, the approach utilizes Whitened Linear Discriminant Analysis to project features into two subspaces - the discriminative and residual subspaces - for which the in-distribution (ID) classes are maximally separated and closely clustered, respectively. The OOD score is then determined by combining the deviation from the input data to the ID pattern in both subspaces. The efficacy of our method, named WDiscOOD, is verified on the large-scale ImageNet-1k benchmark, with six OOD datasets that cover a variety of distribution shifts. WDiscOOD demonstrates superior performance on deep classifiers with diverse backbone architectures, including CNN and vision transformer. Furthermore, we also show that WDiscOOD more effectively detects novel concepts in representation spaces trained with contrastive objectives, including supervised contrastive loss and multi-modality contrastive loss.
Code (1)
Tasks
Novel ConceptsOut-of-Distribution DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
Visual-language models such as CLIP provide powerful general-purpose representations, but their raw embeddings are not optimized for supervised classification, often exhibiting limited class separation and excessive dime…
Dimensionality ReductionClassification of high-dimensional data with spiked covariance matrix structure
We study the classification problem for high-dimensional data with $n$ observations on $p$ features where the $p \times p$ covariance matrix $\Sigma$ exhibits a spiked eigenvalues structure and the vector $\zeta$, given …
ClassificationDimensionality ReductionVocal Bursts Intensity PredictionWhitened CLIP as a Likelihood Surrogate of Images and Captions
Likelihood approximations for images are not trivial to compute and can be useful in many applications. We examine the use of Contrastive Language-Image Pre-training (CLIP) to assess the likelihood of images and captions…
The Geometry of Nonlinear Embeddings in Kernel Discriminant Analysis
Fisher's linear discriminant analysis is a classical method for classification, yet it is limited to capturing linear features only. Kernel discriminant analysis as an extension is known to successfully alleviate the lim…
Learning a Discriminant Latent Space with Neural Discriminant Analysis
Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification, out of distribution detection. Inspire…
ClassificationOut-of-Distribution Detection