Utilizing Graph Generation for Enhanced Domain Adaptive Object Detection

TL;DR

This paper introduces a novel graph generation framework with node refinement and graph optimization modules to improve domain adaptive object detection, achieving state-of-the-art results by better semantic alignment and handling abnormal nodes.

Contribution

The paper proposes a new framework utilizing graph generation, node refinement, and variational inference to enhance domain adaptive object detection beyond existing methods.

Findings

Achieves state-of-the-art performance on three benchmarks.

Effectively refines noisy nodes using a memory bank and contrastive regularization.

Improves semantic alignment by separating domain-specific styles from category-invariant features.

Abstract

The problem of Domain Adaptive in the field of Object Detection involves the transfer of object detection models from labeled source domains to unannotated target domains. Recent advancements in this field aim to address domain discrepancies by aligning pixel-pairs across domains within a non-Euclidean graphical space, thereby minimizing semantic distribution variance. Despite their remarkable achievements, these methods often use coarse semantic representations to model graphs, mainly due to ignoring non-informative elements and failing to focus on precise semantic alignment. Additionally, the generation of coarse graphs inherently introduces abnormal nodes, posing challenges and potentially biasing domain adaptation outcomes. Consequently, we propose a framework, which utilizes the Graph Generation to enhance the quality of DAOD (\method{}). Specifically, we introduce a Node Refinement module that utilizes a memory bank to reconstruct noisy sampled nodes while applying contrastive regularization to noisy features. To enhance semantic alignment, we propose separating domain-specific styles from category invariance encoded within graph covariances, which allows us to selectively remove domain-specific styles while preserving category-invariant information, thus facilitating more accurate semantic alignment across different domains. Furthermore, we propose a Graph Optimization adaptor, leveraging variational inference to mitigate the impact of abnormal nodes. Extensive experimentation across three adaptation benchmarks validates that \method{} achieves state-of-the-art performance in the task of unsupervised domain adaptation.