G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection

TL;DR

This paper introduces G-NAS, a neural architecture search method designed for single domain generalization in object detection, effectively preventing overfitting to easy features and improving performance across diverse unseen domains.

Contribution

The paper proposes G-NAS, a novel NAS framework with a G-loss function that enhances generalization by addressing feature imbalance and overfitting in S-DGOD tasks.

Findings

G-NAS achieves state-of-the-art results on urban-scene datasets.

The G-loss effectively reduces overfitting to non-causal features.

G-NAS outperforms baseline methods in cross-domain object detection.

Abstract

In this paper, we focus on a realistic yet challenging task, Single Domain Generalization Object Detection (S-DGOD), where only one source domain's data can be used for training object detectors, but have to generalize multiple distinct target domains. In S-DGOD, both high-capacity fitting and generalization abilities are needed due to the task's complexity. Differentiable Neural Architecture Search (NAS) is known for its high capacity for complex data fitting and we propose to leverage Differentiable NAS to solve S-DGOD. However, it may confront severe over-fitting issues due to the feature imbalance phenomenon, where parameters optimized by gradient descent are biased to learn from the easy-to-learn features, which are usually non-causal and spuriously correlated to ground truth labels, such as the features of background in object detection data. Consequently, this leads to serious performance degradation, especially in generalizing to unseen target domains with huge domain gaps between the source domain and target domains. To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS. Experimental results on the S-DGOD urban-scene datasets demonstrate that the proposed G-NAS achieves SOTA performance compared to baseline methods. Codes are available at https://github.com/wufan-cse/G-NAS.