Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing

27 Nov 2018Fan YangRyota HinamiYusuke MatsuiSteven LyShin'ichi Satoh

Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years. A downside to diffusion is that it performs slowly in comparison to the naive k-NN search, which causes a non-trivial online computational cost on large datasets... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Image Retrieval Oxf105k Offline Diffusion MAP 95.2% # 1
Image Retrieval Oxf5k Offline Diffusion MAP 96.2% # 1
Image Retrieval Par106k Offline Diffusion mAP 96.2% # 1
Image Retrieval Par6k Offline Diffusion mAP 97.8% # 1