SCOPS: Self-Supervised Co-Part Segmentation
This addresses the need for robust part segmentation that generalizes across object categories without requiring large labeled datasets, though it is incremental over prior self-supervised methods.
The paper tackles the problem of part segmentation without manual annotations by proposing a self-supervised deep learning approach with novel loss functions, resulting in part segments that are more geometrically concentrated and semantically consistent across object instances compared to existing techniques.
Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of manual annotations and can not generalize to unseen object categories. We propose a self-supervised deep learning approach for part segmentation, where we devise several loss functions that aids in predicting part segments that are geometrically concentrated, robust to object variations and are also semantically consistent across different object instances. Extensive experiments on different types of image collections demonstrate that our approach can produce part segments that adhere to object boundaries and also more semantically consistent across object instances compared to existing self-supervised techniques.