Domain-Invariant Proposals based on a Balanced Domain Classifier for Object Detection

TL;DR

This paper proposes a domain-invariant object detection method using a balanced domain classifier and adversarial training within Faster R-CNN, improving detection accuracy across different data domains.

Contribution

It introduces a balanced domain classifier and a learning rate strategy to enhance adversarial training for domain-invariant object detection within Faster R-CNN.

Findings

Effective domain adaptation demonstrated on four datasets.

Improved detection accuracy under domain shifts.

Enhanced stability of adversarial training process.

Abstract

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative adversarial networks, the performance in this field has been improved significantly, especially when training and test data are drawn from similar distributions. However, mismatching distributions, i.e., domain shifts, lead to a significant performance drop. In this paper, we build domain-invariant detectors by learning domain classifiers via adversarial training. Based on the previous works that align image and instance level features, we mitigate the domain shift further by introducing a domain adaptation component at the region level within Faster \mbox{R-CNN}. We embed a domain classification network in the region proposal network~(RPN) using adversarial learning. The RPN can now generate accurate region proposals in different domains by effectively aligning the features between them. To mitigate the unstable convergence during the adversarial learning, we introduce a balanced domain classifier as well as a network learning rate adjustment strategy. We conduct comprehensive experiments using four standard datasets. The results demonstrate the effectiveness and robustness of our object detection approach in domain shift scenarios.