Shi, Guangchen and Wu, Yirui and Palaiahnakote, Shivakumara and Pal, Umapada and Lu, Tong (2021) Arnet: Active-reference network for few-shot image semantic segmentation. In: Proceedings - IEEE International Conference on Multimedia and Expo, 5-9 July 2021, Shenzhen, China.
Full text not available from this repository.Abstract
To make predictions on unseen classes, few-shot segmentation becomes a research focus recently. However, most methods build on pixel-level annotation requiring quantity of manual work. Moreover, inherent information on same-category objects to guide segmentation could have large diversity in feature representation due to differences in size, appearance, layout, and so on. To tackle these problems, we present an active-reference network (ARNet) for few-shot segmentation. The proposed active-reference mechanism not only supports accurately co-occurrent objects in either support or query images, but also relaxes high constraint on pixel-level labeling, allowing for weakly boundary labeling. To extract more intrinsic feature representation, a category-modulation module (CMM) is further applied to fuse features extracted from multiple support images, thus forgetting useless and enhancing contributive information. Experiments on PASCAL-5i dataset show the proposed method achieves a m-IOU score of 56.5 for 1-shot and 59.8 for 5-shot segmentation, being 0.5 and 1.3 higher than current state-of-the-art method. © 2021 IEEE
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Funders: | National Key Research and Development Program of China [Grant No: 2018YFC0407901], Fundamental Research Funds for the Central Universities [Grant No: B200202177] |
| Uncontrolled Keywords: | Computer vision; Image enhancement; Image representation; Pixels; Semantics, Active-reference mechanism; Feature representation; Few-shot learning; Few-shot segmentation; Image semantics; Pixel level; Reference network; Semantic segmentation; Shot segmentation; Weekly-labeled supported, Semantic Segmentation |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Computer Science & Information Technology |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 02 Jul 2024 08:16 |
| Last Modified: | 02 Jul 2024 08:16 |
| URI: | http://eprints.um.edu.my/id/eprint/36121 |
Actions (login required)
 |
View Item |
