Mask Encoding for Single Shot Instance Segmentation
| Autor: | Zhang, Rufeng, Tian, Zhi, Shen, Chunhua, You, Mingyu, Yan, Youliang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN. In contrast, one-stage alternatives cannot compete with Mask R-CNN in mask AP, mainly due to the difficulty of compactly representing masks, making the design of one-stage methods very challenging. In this work, we propose a simple singleshot instance segmentation framework, termed mask encoding based instance segmentation (MEInst). Instead of predicting the two-dimensional mask directly, MEInst distills it into a compact and fixed-dimensional representation vector, which allows the instance segmentation task to be incorporated into one-stage bounding-box detectors and results in a simple yet efficient instance segmentation framework. The proposed one-stage MEInst achieves 36.4% in mask AP with single-model (ResNeXt-101-FPN backbone) and single-scale testing on the MS-COCO benchmark. We show that the much simpler and flexible one-stage instance segmentation method, can also achieve competitive performance. This framework can be easily adapted for other instance-level recognition tasks. Code is available at: https://git.io/AdelaiDet Comment: Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2020 |
| Databáze: | arXiv |
| Externí odkaz: |
|