ARNet: Active-Reference Network for Few-Shot Image Semantic Segmentation

Shi, Guangchen; Wu, Yirui; Palaiahnakote, Shivakumara; Pal, Umapada; Lu, Tong

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 cooccurrent 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-5 i 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.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2021 IEEE International Conference on Multimedia and Expo (ICME)
• Start Date: Jul 5, 2021
• End Date: Jul 9, 2021
• Acceptance Date: Jun 9, 2021
• Online Publication Date: Jun 9, 2021
• Publication Date: Jun 9, 2021
• Deposit Date: Nov 15, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 1945-788X
• Book Title: 2021 IEEE International Conference on Multimedia and Expo (ICME)
• ISBN: 978-1-6654-1152-3
• DOI: https://doi.org/10.1109/ICME51207.2021.9428425