Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment

TL;DR

This paper presents a novel approach for single domain-generalized object detection by diversifying the source domain through augmentations and aligning detections across views, leading to improved performance and calibration.

Contribution

It introduces a domain diversification strategy via augmentation and a detection alignment method, enhancing single domain generalization for object detection.

Findings

Outperforms existing methods in single domain generalization

Effective augmentation improves detection performance

Alignment improves model calibration and accuracy

Abstract

In this work, we tackle the problem of domain generalization for object detection, specifically focusing on the scenario where only a single source domain is available. We propose an effective approach that involves two key steps: diversifying the source domain and aligning detections based on class prediction confidence and localization. Firstly, we demonstrate that by carefully selecting a set of augmentations, a base detector can outperform existing methods for single domain generalization by a good margin. This highlights the importance of domain diversification in improving the performance of object detectors. Secondly, we introduce a method to align detections from multiple views, considering both classification and localization outputs. This alignment procedure leads to better generalized and well-calibrated object detector models, which are crucial for accurate decision-making in safety-critical applications. Our approach is detector-agnostic and can be seamlessly applied to both single-stage and two-stage detectors. To validate the effectiveness of our proposed methods, we conduct extensive experiments and ablations on challenging domain-shift scenarios. The results consistently demonstrate the superiority of our approach compared to existing methods. Our code and models are available at: https://github.com/msohaildanish/DivAlign