Efficient Diffusion on Region Manifolds: Recovering Small Objects With Compact CNN Representations

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2077-2086

Abstract


Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage removes additional computation to adjust the precomputed data. We perform diffusion through a sparse linear system solver, yielding practical query times well below one second. Experimentally, we observe a significant boost in performance of image retrieval with compact CNN descriptors on standard benchmarks, especially when the query object covers only a small part of the image. Small objects have been a common failure case of CNN-based retrieval.

Related Material


[pdf] [arXiv] [poster]
[bibtex]
@InProceedings{Iscen_2017_CVPR,
author = {Iscen, Ahmet and Tolias, Giorgos and Avrithis, Yannis and Furon, Teddy and Chum, Ondrej},
title = {Efficient Diffusion on Region Manifolds: Recovering Small Objects With Compact CNN Representations},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}