arXiv subjects

Ran He

Publications and source records attributed to Ran He.

241 records · Page 14Linked to original sources

arXiv2016

Deep Aesthetic Quality Assessment with Semantic Information

Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content. This paper addresses the correlation issue between automatic aesthetic quality assessment and semantic recognition. We cast the assessment problem as the main task among a multi-task deep model, and argue that semantic recognition task offers the key to address this problem. Based on convolutional neural networks, we employ a single and simple multi-task framework to efficiently utilize the supervision of aesthetic and semantic labels. A correlation item between these two tasks is further introduced to the framework by incorporating the inter-task relationship learning. This item not only provides some useful insight about the correlation but also improves assessment accuracy of the aesthetic task. Particularly, an effective strategy is developed to keep a balance between the two tasks, which facilitates to optimize the parameters of the framework. Extensive experiments on the challenging AVA dataset and Photo.net dataset validate the importance of semantic recognition in aesthetic quality assessment, and demonstrate that multi-task deep models can discover an effective aesthetic representation to achieve state-of-the-art results.

cs.CV↗

arXiv2016

Self-Paced Learning: an Implicit Regularization Perspective

Self-paced learning (SPL) mimics the cognitive mechanism of humans and animals that gradually learns from easy to hard samples. One key issue in SPL is to obtain better weighting strategy that is determined by minimizer function. Existing methods usually pursue this by artificially designing the explicit form of SPL regularizer. In this paper, we focus on the minimizer function, and study a group of new regularizer, named self-paced implicit regularizer that is deduced from robust loss function. Based on the convex conjugacy theory, the minimizer function for self-paced implicit regularizer can be directly learned from the latent loss function, while the analytic form of the regularizer can be even known. A general framework (named SPL-IR) for SPL is developed accordingly. We demonstrate that the learning procedure of SPL-IR is associated with latent robust loss functions, thus can provide some theoretical inspirations for its working mechanism. We further analyze the relation between SPL-IR and half-quadratic optimization. Finally, we implement SPL-IR to both supervised and unsupervised tasks, and experimental results corroborate our ideas and demonstrate the correctness and effectiveness of implicit regularizers.

cs.LG↗

arXiv2016

Locally Imposing Function for Generalized Constraint Neural Networks - A Study on Equality Constraints

This work is a further study on the Generalized Constraint Neural Network (GCNN) model [1], [2]. Two challenges are encountered in the study, that is, to embed any type of prior information and to select its imposing schemes. The work focuses on the second challenge and studies a new constraint imposing scheme for equality constraints. A new method called locally imposing function (LIF) is proposed to provide a local correction to the GCNN prediction function, which therefore falls within Locally Imposing Scheme (LIS). In comparison, the conventional Lagrange multiplier method is considered as Globally Imposing Scheme (GIS) because its added constraint term exhibits a global impact to its objective function. Two advantages are gained from LIS over GIS. First, LIS enables constraints to fire locally and explicitly in the domain only where they need on the prediction function. Second, constraints can be implemented within a network setting directly. We attempt to interpret several constraint methods graphically from a viewpoint of the locality principle. Numerical examples confirm the advantages of the proposed method. In solving boundary value problems with Dirichlet and Neumann constraints, the GCNN model with LIF is possible to achieve an exact satisfaction of the constraints.

cs.NE↗

arXiv2015

Learning Structured Ordinal Measures for Video based Face Recognition

This paper presents a structured ordinal measure method for video-based face recognition that simultaneously learns ordinal filters and structured ordinal features. The problem is posed as a non-convex integer program problem that includes two parts. The first part learns stable ordinal filters to project video data into a large-margin ordinal space. The second seeks self-correcting and discrete codes by balancing the projected data and a rank-one ordinal matrix in a structured low-rank way. Unsupervised and supervised structures are considered for the ordinal matrix. In addition, as a complement to hierarchical structures, deep feature representations are integrated into our method to enhance coding stability. An alternating minimization method is employed to handle the discrete and low-rank constraints, yielding high-quality codes that capture prior structures well. Experimental results on three commonly used face video databases show that our method with a simple voting classifier can achieve state-of-the-art recognition rates using fewer features and samples.

cs.CV↗

arXiv2014

Cross-Modal Learning via Pairwise Constraints

In multimedia applications, the text and image components in a web document form a pairwise constraint that potentially indicates the same semantic concept. This paper studies cross-modal learning via the pairwise constraint, and aims to find the common structure hidden in different modalities. We first propose a compound regularization framework to deal with the pairwise constraint, which can be used as a general platform for developing cross-modal algorithms. For unsupervised learning, we propose a cross-modal subspace clustering method to learn a common structure for different modalities. For supervised learning, to reduce the semantic gap and the outliers in pairwise constraints, we propose a cross-modal matching method based on compound ?21 regularization along with an iteratively reweighted algorithm to find the global optimum. Extensive experiments demonstrate the benefits of joint text and image modeling with semantically induced pairwise constraints, and show that the proposed cross-modal methods can further reduce the semantic gap between different modalities and improve the clustering/retrieval accuracy.

cs.CV↗

arXiv2013

ReBe2B5O11 (Re = Y, Gd)- A Series of Rare Earth Beryllium Borates as Deep-Ultraviolet Nonlinear Optical Materials

The rapid developments of the deep-ultraviolet (deep-UV) laser science and technology urgently demand the nonlinear optical crystals which have large band gap enough to transmit the deep-UV light. Herein, we synthesized a series of new rare earth beryllium borates: ReBe2B5O11 (Re = Y, Gd). The structures of all these materials, for both alpha and beta phases, are featured by a novel platelike infinite superlayer [Be2B5O11]3-. Each [Be2B5O11]3- layer is further connected to the neighbor superlayer through Re3+ cations coordinating with O atoms. The beta-ReBe2B5O11 (Re=Y, Gd) have relatively large nonlinear optical coefficients and short UV cut-off wavelength below 200nm. Our investigations indicate that they are promising deep-UV NLO crystals.

cond-mat.mtrl-sci↗

arXiv2011

Information-Theoretic Measures for Objective Evaluation of Classifications

This work presents a systematic study of objective evaluations of abstaining classifications using Information-Theoretic Measures (ITMs). First, we define objective measures for which they do not depend on any free parameter. This definition provides technical simplicity for examining "objectivity" or "subjectivity" directly to classification evaluations. Second, we propose twenty four normalized ITMs, derived from either mutual information, divergence, or cross-entropy, for investigation. Contrary to conventional performance measures that apply empirical formulas based on users' intuitions or preferences, the ITMs are theoretically more sound for realizing objective evaluations of classifications. We apply them to distinguish "error types" and "reject types" in binary classifications without the need for input data of cost terms. Third, to better understand and select the ITMs, we suggest three desirable features for classification assessment measures, which appear more crucial and appealing from the viewpoint of classification applications. Using these features as "meta-measures", we can reveal the advantages and limitations of ITMs from a higher level of evaluation knowledge. Numerical examples are given to corroborate our claims and compare the differences among the proposed measures. The best measure is selected in terms of the meta-measures, and its specific properties regarding error types and reject types are analytically derived.

cs.CV↗