Object-Aware Domain Generalization for Object Detection

Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. Our code is available at https://github.com/WoojuLee24/OA-DG.

Authors

• Wooju Lee Korea Advanced Institute of Science and Technology (KAIST)
• Dasol Hong Urban Robotics Lab, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea
• Hyungtae Lim Urban Robotics Lab, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea
• Hyun Myung Korea Advanced Institute of Science and Technology (KAIST)

Keywords

• CV: Object Detection & Categorization
• CV: Representation Learning for Vision
• CV: Vision for Robotics & Autonomous Driving
• ML: Transfer, Domain Adaptation, Multi-Task Learning