Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
10-2024
Abstract
Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from in-distribution (ID) data in various dimensions, such as foreground features (e.g., objects in CIFAR100 images vs. those in CIFAR10 images) and background features (e.g., textural images vs. objects in CIFAR10). Existing methods can confound foreground and background features in training, failing to utilize the background features for OOD detection. This paper considers the importance of feature disentanglement in out-of-distribution detection and proposes the simultaneous exploitation of both foreground and background features to support the detection of OOD inputs in in out-of-distribution detection. To this end, we propose a novel framework that first disentangles foreground and background features from ID training samples via a dense prediction approach, and then learns a new classifier that can evaluate the OOD scores of test images from both foreground and background features. It is a generic framework that allows for a seamless combination with various existing OOD detection methods. Extensive experiments show that our approach 1) can substantially enhance the performance of four different state-of-the-art (SotA) OOD detection methods on multiple widely-used OOD datasets with diverse background features, and 2) achieves new SotA performance on these benchmarks.
Keywords
Machine learning, Computer vision, Image representation, Anomaly detection, Out-of-Distribution detection, Disentangled representations
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering; Intelligent Systems and Optimization
Publication
Proceedings of 32nd ACM International Conference on Multimedia (ACM MM 2024) : Melbourne, Australia, October 28 - November 1
First Page
8923
Last Page
8931
Identifier
10.1145/3664647.3681614
Publisher
ACM Digital Library
City or Country
Melbourne, Australia
Citation
DING, Choubo and PANG, Guansong.
Improving out-of-distribution detection with disentangled foreground and background features. (2024). Proceedings of 32nd ACM International Conference on Multimedia (ACM MM 2024) : Melbourne, Australia, October 28 - November 1. 8923-8931.
Available at: https://ink.library.smu.edu.sg/sis_research/9756
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3664647.3681614
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons
