Yan Pan

Simultaneous feature learning and hash coding with deep neural networks

Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. For most existing hashing methods, an image is first encoded as a vector of hand-engineering visual features, followed by another separate projection or quantization step that generates binary codes. However, such visual feature vectors may not be optimally compatible with the coding process, thus producing sub-optimal hashing codes. In this paper, we propose a deep architecture for supervised hashing, in which images are mapped into binary codes via carefully designed deep neural networks. The pipeline of the proposed deep architecture consists of three building blocks: 1) a sub-network with a stack of convolution layers to produce the effective intermediate image features; 2) a divide-and-encode module to divide the intermediate image features into multiple branches, each encoded into one hash bit; and 3) a triplet ranking loss designed to characterize that one image is more similar to the second image than to the third one. Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods.

Sparse Learning-to-Rank via an Efficient Primal-Dual Algorithm

Learning-to-rank for information retrieval has gained increasing interest in recent years. Inspired by the success of sparse models, we consider the problem of sparse learning-to-rank, where the learned ranking models are constrained to be with only a few nonzero coefficients. We begin by formulating the sparse learning-to-rank problem as a convex optimization problem with a sparse-inducing

FSMRank: Feature Selection Algorithm for Learning to Rank

(\ell_1)

Deep Recurrent Regression for Facial Landmark Detection

constraint. Since the

Efficient k-Support Matrix Pursuit

(\ell_1)

Greedy feature selection for ranking

constraint is nondifferentiable, the critical issue arising here is how to efficiently solve the optimization problem. To address this issue, we propose a learning algorithm from the primal dual perspective. Furthermore, we prove that, after at most

A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit

(O({1\over \epsilon } ))

Transductive learning to rank using association rules

iterations, the proposed algorithm can guarantee the obtainment of an

Margin-based two-stage supervised hashing for image retrieval

(\epsilon)

A Divide-and-Conquer Method for Scalable Robust Multitask Learning

-accurate solution. This convergence rate is better than that of the popular subgradient descent algorithm. i.e.,