We present a novel compact image descriptor for large scale image search. Our proposed descriptor - Geometric VLAD (gVLAD) is an extension of VLAD (Vector of Locally Aggregated Descriptors) that incorporates weak geometry information into the VLAD framework. The proposed geometry cues are derived as a membership function over keypoint angles which contain evident and informative information but yet often discarded. A principled technique for learning the membership function by clustering angles is also presented. Further, to address the overhead of iterative codebook training over real-time datasets, a novel codebook adaptation strategy is outlined. Finally, we demonstrate the efficacy of proposed gVLAD based retrieval framework where we achieve more than 15% improvement in mAP over existing benchmarks.
@article{arxiv.1403.3829,
title = {Geometric VLAD for Large Scale Image Search},
author = {Zixuan Wang and Wei Di and Anurag Bhardwaj and Vignesh Jagadeesh and Robinson Piramuthu},
journal= {arXiv preprint arXiv:1403.3829},
year = {2014}
}