Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
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.
Cite
Text
Iscen et al. "Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.105Markdown
[Iscen et al. "Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/iscen2017cvpr-efficient/) doi:10.1109/CVPR.2017.105BibTeX
@inproceedings{iscen2017cvpr-efficient,
title = {{Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations}},
author = {Iscen, Ahmet and Tolias, Giorgos and Avrithis, Yannis and Furon, Teddy and Chum, Ondrej},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2017},
doi = {10.1109/CVPR.2017.105},
url = {https://mlanthology.org/cvpr/2017/iscen2017cvpr-efficient/}
}