ServiceNow Research

Proposal-based Instance Segmentation with Point Supervision

Abstract

Instance segmentation methods often require costly per-pixel labels. We propose a method called WISE-Net that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output full segmentation masks. To address this challenge, we construct a network with two branches: (1) a 10-calization network (L-Net) that predicts the location of each object; and (2) an embedding network (E-Net) that learns an embedding space where pixels of the same object are close. The segmentation masks for the located objects are obtained by grouping pixels with similar embeddings. We evaluate our approach on PASCAL VOC, COCO, KITTI and CityScapes datasets. The experiments show that our method (1) obtains competitive results compared to fully-supervised methods in certain scenarios; (2) outperforms fully-and weakly-supervised methods with a fixed annotation budget; and (3) establishes a first strong baseline for instance segmentation with point-level supervision.

Publication
International Conference on Image Processing (ICIP)
Issam H. Laradji
Issam H. Laradji
Research Scientist

Research Scientist at Low Data Learning located at Vancouver, BC, Canada.

David Vazquez
David Vazquez
Manager of Research Programs

Manager of Research Programs at Research Management located at Montreal, QC, Canada.