Domain Decorrelation with Potential Energy Ranking

Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Shiming Xiang, Gaofeng Meng*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

1 Citation (Scopus)

Abstract

Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under ideal experimental settings. Generally, these classic deep learning methods are built on the i.i.d. assumption, supposing the training and test data are drawn from the same distribution independently and identically. However, the aforementioned i.i.d. assumption is, in general, unavailable in the real-world scenarios, and as a result, leads to sharp performance decay of deep learning algorithms. Behind this, domain shift is one of the primary factors to be blamed. In order to tackle this problem, we propose using Potential Energy Ranking (PoER) to decouple the object feature and the domain feature in given images, promoting the learning of label-discriminative representations while filtering out the irrelevant correlations between the objects and the background. PoER employs the ranking loss in shallow layers to make features with identical category and domain labels close to each other and vice versa. This makes the neural networks aware of both objects and background characteristics, which is vital for generating domain-invariant features. Subsequently, with the stacked convolutional blocks, PoER further uses the contrastive loss to make features within the same categories distribute densely no matter domains, filtering out the domain information progressively for feature alignment. PoER reports superior performance on domain generalization benchmarks, improving the average top-1 accuracy by at least 1.20% compared to the existing methods. Moreover, we use PoER in the ECCV 2022 NICO Challenge, achieving top place with only a vanilla ResNet-18 and winning the jury award. The code has been made publicly available at: https://github.com/ForeverPs/PoER.

Original languageEnglish
Title of host publicationProceedings of 37th AAAI Conference on Artificial Intelligence, AAAI 2023
EditorsBrian Williams, Yiling Chen, Jennifer Neville
Place of PublicationWashington, DC
PublisherAAAI press
Pages2020-2028
Number of pages9
Edition1st
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 27 Jun 2023
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023
https://ojs.aaai.org/index.php/AAAI/issue/view/553
https://aaai-23.aaai.org/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number2
Volume37
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
CityWashington
Period7/02/2314/02/23
Internet address

Scopus Subject Areas

  • Artificial Intelligence

Cite this