Image Segmentation-based Unsupervised Multiple Objects Discovery
This addresses the problem of localizing objects without annotations for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles unsupervised object discovery by proposing a two-stage bottom-up approach that segments object parts using self-supervised features and merges them with CNN models, achieving state-of-the-art results in class-agnostic object detection and image segmentation with improved precision-recall trade-off.
Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for multiple objects discovery. The proposed approach is a two-stage framework. First, instances of object parts are segmented by using the intra-image similarity between self-supervised local features. The second step merges and filters the object parts to form complete object instances. The latter is performed by two CNN models that capture semantic information on objects from the entire dataset. We demonstrate that the pseudo-labels generated by our method provide a better precision-recall trade-off than existing single and multiple objects discovery methods. In particular, we provide state-of-the-art results for both unsupervised class-agnostic object detection and unsupervised image segmentation.