Diffusing More Objects for Semi-Supervised Domain Adaptation with Less Labeling
This addresses the need for reduced labeling effort in domain adaptation for object detection, though it is incremental as it builds on existing diffusion and semi-supervised methods.
The paper tackles the problem of semi-supervised domain adaptation for object detection by using a diffusion model to generate pseudo-labels from unlabeled images, achieving performance on par with human-selected pseudo-labels without human involvement.
For object detection, it is possible to view the prediction of bounding boxes as a reverse diffusion process. Using a diffusion model, the random bounding boxes are iteratively refined in a denoising step, conditioned on the image. We propose a stochastic accumulator function that starts each run with random bounding boxes and combines the slightly different predictions. We empirically verify that this improves detection performance. The improved detections are leveraged on unlabelled images as weighted pseudo-labels for semi-supervised learning. We evaluate the method on a challenging out-of-domain test set. Our method brings significant improvements and is on par with human-selected pseudo-labels, while not requiring any human involvement.