Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection

TL;DR

This paper introduces a Frequency Spectrum Augmentation Consistency framework for domain adaptive object detection, improving generalization across different data domains by using augmented data and a two-stage training process.

Contribution

It proposes a novel FSAC framework with frequency-based augmentations and a two-stage optimization, addressing semantic gaps in domain adaptation for object detection.

Findings

Effective on single-target DAOD tasks

Improves prediction consistency with pseudo labels

Demonstrates superiority over baseline methods

Abstract

Domain adaptive object detection (DAOD) aims to improve the generalization ability of detectors when the training and test data are from different domains. Considering the significant domain gap, some typical methods, e.g., CycleGAN-based methods, adopt the intermediate domain to bridge the source and target domains progressively. However, the CycleGAN-based intermediate domain lacks the pix- or instance-level supervision for object detection, which leads to semantic differences. To address this problem, in this paper, we introduce a Frequency Spectrum Augmentation Consistency (FSAC) framework with four different low-frequency filter operations. In this way, we can obtain a series of augmented data as the intermediate domain. Concretely, we propose a two-stage optimization framework. In the first stage, we utilize all the original and augmented source data to train an object detector. In the second stage, augmented source and target data with pseudo labels are adopted to perform the self-training for prediction consistency. And a teacher model optimized using Mean Teacher is used to further revise the pseudo labels. In the experiment, we evaluate our method on the single- and compound- target DAOD separately, which demonstrate the effectiveness of our method.