Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection
Authors:
- Marc LafonMLMarc Lafon
- Elias RamziERElias Ramzi
- Clément RambourCRClément Rambour
- Nicolas ThomeNTNicolas Thome
Preprint
Abstract
Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to compose several energy terms. Extensive experiments demonstrate the significance of the two contributions. HEAT sets new state-of-the-art OOD detection results on the CIFAR-10 / CIFAR-100 benchmark as well as on the large-scale Imagenet benchmark. The code is available at: https://github.com/MarcLafon/heatood.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- ViM: Out-Of-Distribution with Virtual-logit Matching2022
- Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Computer Vision for Autonomous VehiclesFoundations and Trends in Computer Graphics and Vision, 2020
- TossingBot: Learning to Throw Arbitrary Objects with Residual Physics2019
- Places: A 10 Million Image Database for Scene RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Towards Open Set Deep Networks2016
- Towards Open World Recognition2015
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002