UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation

Chen, Jiacheng; Gao, Bin-Bin; Lu, Zongqing; Xue, Jing-Hao; Wang, Chengjie; Liao, Qingmin; (2022) APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation. IEEE Transactions on Multimedia 10.1109/tmm.2022.3174405. (In press). Green open access

[thumbnail of JiachengChen-BinBinGao-TMM-2022.pdf]
Preview
Text
JiachengChen-BinBinGao-TMM-2022.pdf - Accepted Version

Download (12MB) | Preview

Abstract

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to incomplete feature comparisons. To address this issue, we present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes and thus construct complete sample pairs for learning semantic alignment with query features. The complementary features learning manner effectively enriches feature comparison and helps yield an unbiased segmentation model in the few-shot setting. It is implemented with a two-branch end-to-end network (\ie, a class-specific branch and a class-agnostic branch), which generates prototypes and then combines query features to perform comparisons. In addition, the proposed class-agnostic branch is simple yet effective. In practice, it can adaptively generate multiple class-agnostic prototypes for query images and learn feature alignment in a self-contrastive manner. Extensive experiments on PASCAL-5 i and COCO-20 i demonstrate the superiority of our method. At no expense of inference efficiency, our model achieves state-of-the-art results in both 1-shot and 5-shot settings for few-shot semantic segmentation.

Type: Article
Title: APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tmm.2022.3174405
Publisher version: https://doi.org/10.1109/tmm.2022.3174405
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Prototypes, Training, Semantics, Image segmentation, Measurement, Testing, Feature extraction
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10149026
Downloads since deposit
92Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item