1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track

TL;DR

This paper presents a novel Generalize-then-Adapt framework combining domain generalization and source-free domain adaptation to improve out-of-distribution object detection, achieving first place in the ECCV 2022 OOD-CV challenge.

Contribution

The paper introduces a simple yet effective G&A framework that integrates two-stage domain generalization with source-free domain adaptation for object detection.

Findings

Achieved first place in the OOD-CV challenge leaderboard.

Demonstrated the effectiveness of combining domain generalization and adaptation.

Provided code for reproducibility.

Abstract

OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage domain generalization part and a one-stage domain adaptation part. The domain generalization part is implemented by a Supervised Model Pretraining stage using source data for model warm-up and a Weakly Semi-Supervised Model Pretraining stage using both source data with box-level label and auxiliary data (ImageNet-1K) with image-level label for performance boosting. The domain adaptation part is implemented as a Source-Free Domain Adaptation paradigm, which only uses the pre-trained model and the unlabeled target data to further optimize in a self-supervised training manner. The proposed G&A framework help us achieve the first place on the object detection leaderboard of the OOD-CV challenge. Code will be released in https://github.com/hikvision-research/OOD-CV.