From selective deep convolutional features to compact binary representations for image retrieval

Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, Huu Le, Tam V. Nguyen, Ngai Man Cheung

Research output: Contribution to journalArticleResearchpeer-review

18 Citations (Scopus)


In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional Neural Network is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this article, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we first propose various strategies to compute masks, namely, SIFT-masks, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and eliminate redundant features. Our in-depth analyses demonstrate that proposed masking schemes are effective to address the burstiness drawback and improve retrieval accuracy. Second, we propose to employ recent embedding and aggregating methods that can significantly boost the feature discriminability. Regarding the computation and storage efficiency, we include a hashing module to produce very compact binary image representations. Extensive experiments on six image retrieval benchmarks demonstrate that our proposed framework achieves the state-of-the-art retrieval performances.

Original languageEnglish
Article numbera43
Number of pages22
JournalACM Transactions on Multimedia Computing, Communications and Applications
Issue number2
Publication statusPublished - Jun 2019
Externally publishedYes


  • Aggregating
  • Content based image retrieval
  • Deep convolutional features
  • Embedding
  • Image hashing
  • Unsupervised

Cite this