You are here

Saliency Weighted Convolutional Features for Instance Search


Eva Mohedano, Kevin McGuinness, Xavier Giro-i-Nieto, Noel O'Connor

Publication Type: 
Refereed Conference Meeting Proceeding
This work explores attention models to weight the contribution of local convolutional representations for the instance search task. We present a retrieval framework based on bags of local convolutional features (BLCF) that benefits from saliency weighting to build an efficient image representation. The use of human visual attention models (saliency) allows significant improvements in retrieval performance without the need to conduct region analysis or spatial verification, and without requiring any feature fine tuning. We investigate the impact of different saliency models, finding that higher performance on saliency benchmarks does not necessarily equate to improved performance when used in instance search tasks. The proposed approach outperforms the state-of-the-art on the challenging INSTRE benchmark by a large margin, and provides similar performance on the Oxford and Paris benchmarks compared to more complex methods that use off-the-shelf representations. Source code is publicly available at Index Terms—Instance Retrieval, Convolutional Neural Networks, Bag of Words, Saliency weighting
Conference Name: 
16th International Conference on Content-Based Multimedia Indexing (CBMI)
Digital Object Identifer (DOI): 
Publication Date: 
Conference Location: 
Research Group: 
Dublin City University (DCU)
Open access repository: