Geometric VLAD for Large Scale Image Search

2014/03/15 by Wang, Zixuan, Di, Wei, Bhardwaj, Anurag +2
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1403.3829

Abstract

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.

Related

• Voronoi-based compact image descriptors: Efficient Region-of-Interest\n retrieval with VLAD and deep-learning-based descriptors
• A Dense-Depth Representation for VLAD descriptors in Content-Based Image\n Retrieval
• Deep Image Retrieval: Learning global representations for image search
• Large-Scale Image Retrieval with Attentive Deep Local Features
• Local Feature Detectors, Descriptors, and Image Representations: A Survey