Few-shot Adaptive Object Detection with Cross-Domain CutMix

TL;DR

This paper introduces a cross-domain CutMix data augmentation technique for few-shot object detection, effectively bridging large domain gaps such as RGB to thermal infrared and simulation to real images.

Contribution

It proposes a novel data synthesis method with adversarial learning to improve object detection across significantly different domains using limited target data.

Findings

Outperforms conventional methods in thermal infrared detection from RGB images.

Achieves higher accuracy in simulation-to-real image transfer.

Effective in scenarios with very few target domain samples.

Abstract

In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer learning and domain adaptation cannot bridge the domain gap when the target domain differs significantly from the source domain. We propose a data synthesis method that can solve the large domain gap problem. In this method, a part of the target image is pasted onto the source image, and the position of the pasted region is aligned by utilizing the information of the object bounding box. In addition, we introduce adversarial learning to discriminate whether the original or the pasted regions. The proposed method trains on a large number of source images and a few target domain images. The proposed method achieves higher accuracy than conventional methods in a very different domain problem setting, where RGB images are the source domain, and thermal infrared images are the target domain. Similarly, the proposed method achieves higher accuracy in the cases of simulation images to real images.