Arnet: Active-reference network for few-shot image semantic segmentation
Document Type
Conference Item
Publication Date
1-1-2021
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
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
Divisions
fsktm
Funders
National Key Research and Development Program of China [Grant No: 2018YFC0407901],Fundamental Research Funds for the Central Universities [Grant No: B200202177]
Publication Title
Proceedings - IEEE International Conference on Multimedia and Expo
Event Title
Proceedings - IEEE International Conference on Multimedia and Expo
Event Location
Shenzhen, China
Event Dates
5-9 July 2021
Event Type
conference