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

Publication Type:
Conference Proceeding
31st AAAI Conference on Artificial Intelligence, AAAI 2017, 2017, pp. 1524 - 1531
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
14688-66430-1-PB.pdfPublished version2.97 MB
Adobe PDF
Copyright © 2017, Association for the Advancement of Artificial Intelligence ( All rights reserved. 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.
Please use this identifier to cite or link to this item: