Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

TL;DR

This paper proposes a two-stage domain adaptive representation learning framework for object detection, combining domain diversification and multi-domain-invariant feature learning to improve adaptation performance.

Contribution

It introduces a novel two-stage paradigm that addresses pixel-level translation issues and feature discriminativity bias in unsupervised domain adaptation for object detection.

Findings

Outperforms state-of-the-art methods by 3-11% mAP

Effectively mitigates imperfect image translation issues

Enhances feature invariance across diverse domains

Abstract

We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations simultaneously. Our approach is composed of two stages, i.e., Domain Diversification (DD) and Multi-domain-invariant Representation Learning (MRL). At the DD stage, we diversify the distribution of the labeled data by generating various distinctive shifted domains from the source domain. At the MRL stage, we apply adversarial learning with a multi-domain discriminator to encourage feature to be indistinguishable among the domains. DD addresses the source-biased discriminativity, while MRL mitigates the imperfect image translation. We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation. Our method outperforms the state-of-the-art methods by a large margin of 3%~11% in terms of mean average precision (mAP) on various datasets.