Adapting Object Detectors with Conditional Domain Normalization

TL;DR

This paper introduces Conditional Domain Normalization (CDN), a novel method for adapting object detectors across different domains by encoding domain attributes into features, significantly improving performance on various benchmarks.

Contribution

The paper proposes CDN, a new normalization technique that encodes domain attributes into features, enabling effective domain adaptation for object detection tasks.

Findings

CDN outperforms existing methods on real-to-real and synthetic-to-real benchmarks.

CDN improves object detection accuracy across 2D images and 3D point clouds.

Extensive experiments validate CDN's effectiveness in reducing domain gaps.

Abstract

Real-world object detectors are often challenged by the domain gaps between different datasets. In this work, we present the Conditional Domain Normalization (CDN) to bridge the domain gap. CDN is designed to encode different domain inputs into a shared latent space, where the features from different domains carry the same domain attribute. To achieve this, we first disentangle the domain-specific attribute out of the semantic features from one domain via a domain embedding module, which learns a domain-vector to characterize the corresponding domain attribute information. Then this domain-vector is used to encode the features from another domain through a conditional normalization, resulting in different domains' features carrying the same domain attribute. We incorporate CDN into various convolution stages of an object detector to adaptively address the domain shifts of different level's representation. In contrast to existing adaptation works that conduct domain confusion learning on semantic features to remove domain-specific factors, CDN aligns different domain distributions by modulating the semantic features of one domain conditioned on the learned domain-vector of another domain. Extensive experiments show that CDN outperforms existing methods remarkably on both real-to-real and synthetic-to-real adaptation benchmarks, including 2D image detection and 3D point cloud detection.