D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation

TL;DR

This paper introduces D2DF2WOD, a dual-domain framework that enhances weakly-supervised object detection by leveraging synthetic data and domain adaptation to improve object proposals and localization accuracy.

Contribution

The paper proposes a novel dual-domain approach combining fully-supervised and weakly-supervised learning with domain adaptation to improve object detection in weakly-labeled images.

Findings

Consistently outperforms state-of-the-art methods on five benchmarks.

Improves object proposal quality through domain adaptation.

Enhances localization accuracy in weakly-supervised detection.

Abstract

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at inference time. To tackle this issue, we propose D2DF2WOD, a Dual-Domain Fully-to-Weakly Supervised Object Detection framework that leverages synthetic data, annotated with precise object localization, to supplement a natural image target domain, where only image-level labels are available. In its warm-up domain adaptation stage, the model learns a fully-supervised object detector (FSOD) to improve the precision of the object proposals in the target domain, and at the same time learns target-domain-specific and detection-aware proposal features. In its main WSOD stage, a WSOD model is specifically tuned to the target domain. The feature extractor and the object proposal generator of the WSOD model are built upon the fine-tuned FSOD model. We test D2DF2WOD on five dual-domain image benchmarks. The results show that our method results in consistently improved object detection and localization compared with state-of-the-art methods.