Selective Deep Convolutional Features for Image Retrieval

Abstract

Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different approach, in this paper, we propose a novel framework to achieve competitive retrieval performance. Firstly, we propose various masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and remove a large number of redundant features. We demonstrate that this can effectively address the burstiness issue and improve retrieval accuracy. Secondly, we propose to employ recent embedding and aggregating methods to further enhance feature discriminability. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art retrieval accuracy.

Accepted to ACM MM 2017

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YFCC100M: The New Data in Multimedia Research
• MatConvNet - Convolutional Neural Networks for MATLAB
• Deep Image Retrieval: Learning global representations for image search
• Learning to Hash with Binary Deep Neural Network
• Simultaneous Feature Aggregating and Hashing for Large-scale Image Search

Cited by in corpus (3)

• Efficient and Deep Person Re-Identification using Multi-Level Similarity
• From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
• Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing