Geometric VLAD for Large Scale Image Search
This work addresses image retrieval efficiency and accuracy for applications like visual search, though it appears incremental as it builds on the VLAD framework.
The paper tackles the problem of large-scale image search by proposing Geometric VLAD (gVLAD), a compact image descriptor that incorporates weak geometry information from keypoint angles, achieving more than 15% improvement in mAP over existing benchmarks.
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.