Few-shot Adaptive Object Detection with Cross-Domain CutMix
This addresses the labor-intensive data collection problem in object detection for domains with significant differences from available datasets, though it appears incremental as an adaptation of existing techniques like CutMix and adversarial learning.
The paper tackles the problem of object detection when there's a large domain gap between source and target domains, such as RGB to thermal infrared images, by proposing a data synthesis method that pastes target image regions onto source images with bounding box alignment and adversarial learning. The method achieves higher accuracy than conventional methods in these challenging cross-domain settings.
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.