Prototype Mixture Models for Few-shot Semantic Segmentation release_zcugqugx55czbfixsy6vyag4ym

by Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye

Released as a article .

2020  

Abstract

Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82\% with only a moderate cost for model size and inference speed.
In text/plain format

Archived Files and Locations

application/pdf  1.7 MB
file_ldmrsfd2mfadnbwnwbv2s4sede
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-08-10
Version   v1
Language   en ?
arXiv  2008.03898v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2dae3c7a-4e04-46c6-a671-4facc6e0f554
API URL: JSON