Ensemble Diffusion for Retrieval

Song Bai, Zhichao Zhou, Jingdong Wang, Xiang Bai, Longin Jan Latecki, Qi Tian; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 774-783

Abstract


As a postprocessing procedure, diffusion process has demonstrated its ability of substantially improving the performance of various visual retrieval systems. Whereas, great efforts are also devoted to similarity (or metric) fusion, seeing that only one individual type of similarity cannot fully reveal the intrinsic relationship between objects. This stimulates a great research interest of considering similarity fusion in the framework of diffusion process (i.e., fusion with diffusion) for robust retrieval. In this paper, we firstly revisit representative methods about fusion with diffusion, and provide new insights which are ignored by previous researchers. Then, observing that existing algorithms are susceptible to noisy similarities, the proposed Regularized Ensemble Diffusion (RED) is bundled with an automatic weight learning paradigm, so that the negative impacts of noisy similarities are suppressed. At last, we integrate several recently-proposed similarities with the proposed framework. The experimental results suggest that we can achieve new state-of-the-art performances on various retrieval tasks, including 3D shape retrieval on ModelNet dataset, and image retrieval on Holidays and Ukbench dataset.

Related Material


[pdf] [Supp] [video]
[bibtex]
@InProceedings{Bai_2017_ICCV,
author = {Bai, Song and Zhou, Zhichao and Wang, Jingdong and Bai, Xiang and Jan Latecki, Longin and Tian, Qi},
title = {Ensemble Diffusion for Retrieval},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}