paper-with-me

Papers

On the Out-of-distribution Generalization of Probabilistic Image Modelling

2021-09-04 · NeurIPS 2021 12 · Mingtian Zhang, Andi Zhang, Steven McDonagh

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.

📄 PDF Abstract BibTeX arXiv:2109.02639

Code (2)

zmtomorrow/nelloc 공식 구현 pytorch
zmtomorrow/parallelnelloc pytorch

Tasks

Out-of-Distribution GeneralizationOut of Distribution (OOD) Detection

Similar Papers 제목 키워드 기반

Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE

2020-07-09 · Anna Volokitin, Ertunc Erdil, Neerav Karani, Kerem Can Tezcan 외

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 Analysis

ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees

2019-05-01 · ICLR 2019 5 · Hao He, Hao Wang, Guang-He Lee, Yonglong Tian

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 Generation

Interpretable Probabilistic Medical Image Segmentation via Gaussian Process with Explicit Modelling of Annotation Bias and Variability

2026-06-22 · Qi Li, Yuliang Huang, Shaheer U. Saeed, Qianye Yang 외 arxiv

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 Segmentation

Robust Hybrid Learning With Expert Augmentation

2022-02-08 · Antoine Wehenkel, Jens Behrmann, Hsiang Hsu, Guillermo Sapiro 외

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

Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors

2013-08-01 · ACL 2013 8 · Jackie Chi Kit Cheung, Gerald Penn
Document SummarizationMulti-Document SummarizationText Generation