Object-Aware Domain Generalization for Object Detection

2023-12-19 · Wooju Lee, Dasol Hong, Hyungtae Lim, Hyun Myung

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.

📄 PDF Abstract BibTeX arXiv:2312.12133

Code (1)

WoojuLee24/OA-DG 공식 구현 pytorch

Tasks

Autonomous Driving Contrastive Learning Data Augmentation Domain GeneralizationObjectobject-detection Object Detection Object Localization Robust Object Detection

Methods 이 논문이 사용한 방법론

OA-Loss OA-Loss reduces the domain gap between the original and augmented images. OA-Loss enables the model to learn semantic relations of foreground and background instances from…

OA-Mix OA-Mix is a general and effective data augmentation method for single-domain generalization in object detection. It increases image diversity while preserving important…

Domain Generalization of 3D Object Detection by Density-Resampling

2023-11-17 · Shuangzhi Li, Lei Ma, Xingyu Li

Point-cloud-based 3D object detection suffers from performance degradation when encountering data with novel domain gaps. To tackle it, the single-domain generalization (SDG) aims to generalize the detection model traine…

3D Object Detection Data Augmentation Domain Adaptation Domain Generalization+6

GOOD: Towards Domain Generalized Orientated Object Detection

2024-02-20 · Qi Bi, Beichen Zhou, Jingjun Yi, Wei Ji 외

Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this…

Hallucination Object object-detection Object Detection+1

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

2024-02-07 · Fan Wu, Jinling Gao, Lanqing Hong, Xinbing Wang 외

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 m…

Domain Generalization Neural Architecture Search object-detection Object Detection

ADOD: Adaptive Domain-Aware Object Detection with Residual Attention for Underwater Environments

2023-12-11 · Lyes Saad Saoud, Zhenwei Niu, Atif Sultan, Lakmal Seneviratne 외

This research presents ADOD, a novel approach to address domain generalization in underwater object detection. Our method enhances the model's ability to generalize across diverse and unseen domains, ensuring robustness …

domain classification Domain Generalization Object object-detection+1

SRDAN: Scale-Aware and Range-Aware Domain Adaptation Network for Cross-Dataset 3D Object Detection

2021-06-19 · CVPR 2021 1 · Weichen Zhang, Wen Li, Dong Xu

Geometric characteristic plays an important role in the representation of an object in 3D point clouds. For example, large objects often contain more points, while small ones contain fewer points. The point clouds of…

3D Object Detection Domain Adaptation Object object-detection+1