On the Out-of-distribution Generalization of Probabilistic Image Modelling
Out-of-distribution (OOD) detection and lossless compression constitute two problems that can be solved by the training of probabilistic models on a first dataset with subsequent likelihood evaluation on a second dataset, where data distributions differ. By defining the generalization of probabilistic models in terms of likelihood we show that, in the case of image models, the OOD generalization ability is dominated by local features. This motivates our proposal of a Local Autoregressive model that exclusively models local image features towards improving OOD performance. We apply the proposed model to OOD detection tasks and achieve state-of-the-art unsupervised OOD detection performance without the introduction of additional data. Additionally, we employ our model to build a new lossless image compressor: NeLLoC (Neural Local Lossless Compressor) and report state-of-the-art compression rates and model size.
Code (2)
Tasks
Out-of-Distribution GeneralizationOut of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE
Probabilistic modelling has been an essential tool in medical image analysis, especially for analyzing brain Magnetic Resonance Images (MRI). Recent deep learning techniques for estimating high-dimensional distributions,…
AnatomyMedical Image AnalysisProbGAN: Towards Probabilistic GAN with Theoretical Guarantees
Probabilistic modelling is a principled framework to perform model aggregation, which has been a primary mechanism to combat mode collapse in the context of Generative Adversarial Networks (GAN). In this paper, we propos…
Image GenerationInterpretable Probabilistic Medical Image Segmentation via Gaussian Process with Explicit Modelling of Annotation Bias and Variability
Deep learning-based medical image segmentation models are trained using annotations that exhibit systematic bias and variability across raters. While probabilistic multi-rater approaches can emulate annotator-specific de…
Medical Image SegmentationRobust Hybrid Learning With Expert Augmentation
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited t…
Data Augmentationvalid