Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
| Autor: | Shai Limonchik, Mehmet Giray Ogut, Zhenzhen Weng, Serena Yeung |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Structure (mathematical logic) Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Supervised learning Computer Science - Computer Vision and Pattern Recognition Pattern recognition Image segmentation Domain (software engineering) Self supervision Pattern recognition (psychology) Segmentation Long tail Artificial intelligence business |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr46437.2021.00263 |
| Popis: | Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarchical structure between objects in the images, we propose self-supervised losses for learning mask embeddings. Trained on COCO [34] dataset without additional annotations of the long-tail objects, our model is able to discover novel and more fine-grained objects than the common categories in COCO. We show that the model achieves competitive quantitative results on LVIS [17] as compared to the supervised and partially supervised methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|