Beyond IID: Learning to combine Non-IID metrics for vision tasks

Yinghuan Shi, Wenbin Li, Yang Gao, Longbing Cao, Dinggang Shen

    Research output: Contribution to conferencePaperpeer-review

    10 Citations (Scopus)

    Abstract

    Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification. The results show that learning and integrating non-IID metrics improves the performance, compared to the IID methods. Moreover, our method achieves results comparable or better than that of the state-of-the-arts.

    Original languageEnglish
    Pages1524-1531
    Number of pages8
    Publication statusPublished - 2017
    Event31st AAAI Conference on Artificial Intelligence, AAAI 2017 - San Francisco, United States
    Duration: 2017 Feb 42017 Feb 10

    Other

    Other31st AAAI Conference on Artificial Intelligence, AAAI 2017
    Country/TerritoryUnited States
    CitySan Francisco
    Period17/2/417/2/10

    Bibliographical note

    Funding Information:
    This research was supported by NSFC (Nos. 61673203, 61305068, 61432008, 61321491), Jiangsu Nature Science Foundation (JSNSF) (No. BK20130581). The authors would like to thank Wanqi Yang and Jing Huo for proofreading.

    Publisher Copyright:
    Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

    ASJC Scopus subject areas

    • Artificial Intelligence

    Fingerprint

    Dive into the research topics of 'Beyond IID: Learning to combine Non-IID metrics for vision tasks'. Together they form a unique fingerprint.

    Cite this