| Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation | |
Dong JH(董家华)1,2,3; Cong Y(丛杨)1,2 ; Sun G(孙干)1,2,3; Hou DD(侯冬冬)1,2,3
| |
| Department | 机器人学研究室 |
| Conference Name | 2019 IEEE/CVF International Conference on Computer Vision (ICCV) |
| Conference Date | October 27 - November 2, 2019 |
| Conference Place | Seoul, Korea |
| Source Publication | 2019 IEEE/CVF International Conference on Computer Vision (ICCV) |
| Publisher | IEEE |
| Publication Place | New York |
| 2019 | |
| Pages | 10712-10721 |
| Indexed By | EI ; CPCI（ISTP） |
| EI Accession number | 20201208327193 |
| WOS ID | WOS:000548549205084 |
| Contribution Rank | 1 |
| Abstract | Weakly-supervised learning under image-level labels supervision has been widely applied to semantic segmentation of medical lesions regions. However, 1) most existing models rely on effective constraints to explore the internal representation of lesions, which only produces inaccurate and coarse lesions regions; 2) they ignore the strong probabilistic dependencies between target lesions dataset (e.g., enteroscopy images) and well-to-annotated source diseases dataset (e.g., gastroscope images). To better utilize these dependencies, we present a new semantic lesions representation transfer model for weakly-supervised endoscopic lesions segmentation, which can exploit useful knowledge from relevant fully-labeled diseases segmentation task to enhance the performance of target weakly-labeled lesions segmentation task. More specifically, a pseudo label generator is proposed to leverage seed information to generate highly-confident pseudo pixel labels by incorporating class balance and super-pixel spatial prior. It can iteratively include more hard-to-transfer samples from weakly-labeled target dataset into training set. Afterwards, dynamically searched feature centroids for same class among different datasets are aligned by accumulating previously-learned features. Meanwhile, adversarial learning is also employed in this paper, to narrow the gap between the lesions among different datasets in output space. Finally, we build a new medical endoscopic dataset with 3659 images collected from more than 1100 volunteers. Extensive experiments on our collected dataset and several benchmark datasets validate the effectiveness of our model. |
| Language | 英语 |
| Citation statistics | |
| Document Type | 会议论文 |
| Identifier | http://ir.sia.cn/handle/173321/26064 |
| Collection | 机器人学研究室 |
| Corresponding Author | Cong Y(丛杨) |
| Affiliation | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016, China 3.University of Chinese Academy of Sciences, Beijing, 100049, China |
| Recommended Citation GB/T 7714 | Dong JH,Cong Y,Sun G,et al. Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation[C]. New York:IEEE,2019:10712-10721. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| Semantic-Transferabl（713KB） | 会议论文 | 开放获取 | CC BY-NC-SA | View Application Full Text | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment