Deep Image Retrieval: Learning global representations for image search

5 Apr 2016Albert GordoJon AlmazanJerome RevaudDiane Larlus

We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Image Retrieval Oxf105k DIR+QE* MAP 87.8% # 3
Image Retrieval Oxf5k DIR+QE* MAP 89% # 3
Image Retrieval Par106k DIR+QE* mAP 90.5% # 3
Image Retrieval Par6k DIR+QE* mAP 93.8% # 3