A New Unsupervised Foreground Object Detection Method

Aiming at the low accuracy of object detection methods based on unsupervised object detection, this paper proposes a foreground object detection method in unlabeled dataset. The basic idea is that correct feature clustering results can guide future object feature extraction, while the accurate foreground object features can improve the accuracy of feature clustering. The proposed method extracts local features from unlabeled images and then clusters features based on minimum feature distances. By matching pairwise images in the same cluster, feature weights are computed through feature correspondence. Finally, the updated feature weights are used to guide feature clustering in the next iteration. We simultaneously group similar images and detect foreground objects after iterations. The experimental results on Caltech256 and Google car side images demonstrate the effectiveness of our method. Furthermore, due to the present unsupervised object detection methods lacking of incremental learning ability, we propose an incremental implementation of our method. The experimental results show the incremental learning method can improve the computation speed greatly.