Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

TL;DR

This paper introduces a method to improve the robustness of object detectors against domain shifts by minimizing backbone feature distortion using Relative Gradient Norm, with techniques applicable across various architectures.

Contribution

It proposes using Relative Gradient Norm to measure and reduce backbone vulnerability, offering new regularization and architectural strategies to enhance out-of-distribution robustness.

Findings

High RGN correlates with lower OOD performance.

Some backbones gain robustness through architecture that limits parameter change.

Proposed techniques significantly improve OOD robustness across datasets.

Abstract

Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-distribution (ID) data and distorting features useful for out-of-distribution (OOD) generalization. We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance. Our analysis of RGN yields interesting findings: some backbones lose OOD robustness during fine-tuning, but others gain robustness because their architecture prevents the parameters from changing too much from the initial model. Given these findings, we present recipes to boost OOD robustness for both types of backbones. Specifically, we investigate regularization and architectural choices for minimizing gradient updates so as to prevent the tuned backbone from losing generalizable features. Our proposed techniques complement each other and show substantial improvements over baselines on diverse architectures and datasets. Code is available at https://github.com/VisionLearningGroup/mind_back.