CVMay 23, 2024

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

arXiv:2405.14497v135 citationsh-index: 19Has CodeCVPR
Originality Incremental advance
AI Analysis

This work addresses domain generalization for object detection with only a single source domain, which is incremental but important for safety-critical applications.

The paper tackles single domain-generalized object detection by proposing a method that diversifies the source domain and aligns detections based on confidence and localization, achieving superior performance over existing methods in challenging domain-shift scenarios.

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

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes