Supervised Edge Attention Network for Accurate Image Instance Segmentation
| Autor: | Licheng Jiao, Shi Lingling, Xier Chen, Yanjie Gao, Haoran Wang, Yanchao Lian |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Association (object-oriented programming) 02 engineering and technology 010501 environmental sciences Object (computer science) 01 natural sciences Minimum bounding box 0202 electrical engineering electronic engineering information engineering Code (cryptography) 020201 artificial intelligence & image processing Segmentation Computer vision Enhanced Data Rates for GSM Evolution Artificial intelligence business Focus (optics) 0105 earth and related environmental sciences |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585822 ECCV (27) |
| DOI: | 10.1007/978-3-030-58583-9_37 |
| Popis: | Effectively keeping boundary of the mask complete is important in instance segmentation. In this task, many works segment instance based on a bounding box from the box head, which means the quality of the detection also affects the completeness of the mask. To circumvent this issue, we propose a fully convolutional box head and a supervised edge attention module in mask head. The box head contains one new IoU prediction branch. It learns association between object features and detected bounding boxes to provide more accurate bounding boxes for segmentation. The edge attention module utilizes attention mechanism to highlight object and suppress background noise, and a supervised branch is devised to guide the network to focus on the edge of instances precisely. To evaluate the effectiveness, we conduct experiments on COCO dataset. Without bells and whistles, our approach achieves impressive and robust improvement compared to baseline models. Code is at https://github.com//IPIU-detection/SEANet. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|