Visible to the public Top Rank Supervised Binary Coding for Visual Search

TitleTop Rank Supervised Binary Coding for Visual Search
Publication TypeConference Paper
Year of Publication2015
AuthorsSong, D., Liu, W., Ji, R., Meyer, D. A., Smith, J. R.
Conference Name2015 IEEE International Conference on Computer Vision (ICCV)
Date Publisheddec
KeywordsBinary codes, coding functions, coding quality enhancement, Computer vision, data sample compression, discrete optimization, encoding, gradient methods, Hamming codes, Hamming distance, Hamming-distance ranking list, Image coding, image datasets, image retrieval, image search accuracy, large-scale computer vision applications, learning (artificial intelligence), online learning algorithm, Optimization, precision optimization, pubcrawl170110, stochastic gradient descent method, stochastic programming, supervised information, surrogate objective optimization, top rank supervised binary coding, Top-RSBC, training time cost reduction, visual search, visualization

In recent years, binary coding techniques are becoming increasingly popular because of their high efficiency in handling large-scale computer vision applications. It has been demonstrated that supervised binary coding techniques that leverage supervised information can significantly enhance the coding quality, and hence greatly benefit visual search tasks. Typically, a modern binary coding method seeks to learn a group of coding functions which compress data samples into binary codes. However, few methods pursued the coding functions such that the precision at the top of a ranking list according to Hamming distances of the generated binary codes is optimized. In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance ranking list towards preserving the supervision information. The core idea is to train the disciplined coding functions, by which the mistakes at the top of a Hamming-distance ranking list are penalized more than those at the bottom. To solve such coding functions, we relax the original discrete optimization objective with a continuous surrogate, and derive a stochastic gradient descent to optimize the surrogate objective. To further reduce the training time cost, we also design an online learning algorithm to optimize the surrogate objective more efficiently. Empirical studies based upon three benchmark image datasets demonstrate that the proposed binary coding approach achieves superior image search accuracy over the state-of-the-arts.

Citation Keysong_top_2015