Large-Scale Image Retrieval with Attentive Deep Local Features
Authors:
- Hyeonwoo NohHNHyeonwoo Noh
- Andre AraujoAAAndre Araujo
- Jack SimJSJack Sim
- Tobias WeyandTWTobias Weyand
- Bohyung HanBHBohyung Han
Top Cited Papers
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3476-3485
Abstract
We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELE (DEep Local Feature). The new feature is based on convolutional neural networks, which are trained only with image-level annotations on a landmark image dataset. To identify semantically useful local features for image retrieval, we also propose an attention mechanism for key point selection, which shares most network layers with the descriptor. This frame-work can be used for image retrieval as a drop-in replacement for other keypoint detectors and descriptors, enabling more accurate feature matching and geometric verification. Our system produces reliable confidence scores to reject false positives-in particular, it is robust against queries that have no correct match in the database. To evaluate the proposed descriptor, we introduce a new large-scale dataset, referred to as Google-Landmarks dataset, which involves challenges in both database and query such as background clutter, partial occlusion, multiple landmarks, objects in variable scales, etc. We show that DELE outperforms the state-of-the-art global and local descriptors in the large-scale setting by significant margins.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Stacked Attention Networks for Image Question Answering2016
- Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging2015
- TILDE: A Temporally Invariant Learned DEtector2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Visual Place Recognition with Repetitive Structures2013
- Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening2012
- Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search2008
- Video Google: a text retrieval approach to object matching in videos2003
- Random sample consensusCommunications of the ACM, 1981