Vector-Decomposed Disentanglement for Domain-Invariant Object Detection

TL;DR

This paper introduces a vector decomposition-based method to disentangle domain-invariant and domain-specific features, enhancing domain adaptation in object detection by improving generalization across different domains.

Contribution

It proposes a novel vector decomposition approach to extract domain-invariant representations, addressing limitations of existing domain alignment methods in object detection.

Findings

Significant performance gains on four domain-shift scenes.

Outperforms baseline methods by around 4% on compound-target cases.

Effective in both single- and compound-target domain adaptation scenarios.

Abstract

To improve the generalization of detectors, for domain adaptive object detection (DAOD), recent advances mainly explore aligning feature-level distributions between the source and single-target domain, which may neglect the impact of domain-specific information existing in the aligned features. Towards DAOD, it is important to extract domain-invariant object representations. To this end, in this paper, we try to disentangle domain-invariant representations from domain-specific representations. And we propose a novel disentangled method based on vector decomposition. Firstly, an extractor is devised to separate domain-invariant representations from the input, which are used for extracting object proposals. Secondly, domain-specific representations are introduced as the differences between the input and domain-invariant representations. Through the difference operation, the gap between the domain-specific and domain-invariant representations is enlarged, which promotes domain-invariant representations to contain more domain-irrelevant information. In the experiment, we separately evaluate our method on the single- and compound-target case. For the single-target case, experimental results of four domain-shift scenes show our method obtains a significant performance gain over baseline methods. Moreover, for the compound-target case (i.e., the target is a compound of two different domains without domain labels), our method outperforms baseline methods by around 4%, which demonstrates the effectiveness of our method.