At train stage, a nonlinear regression was learned on train data to infer class “template” in representation space using semantic embeddings as inputs. At test stage, as one test sample arrives, we first reduce its dimension to representation space, we calculate its similarities to unseen ...
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval INTRODUCTION 这是最近看的一篇文章,论文并没有太多方法上的创新点,但是将神经网络用于现代武器的检索,方向挺新奇的。所以记录一下。论文之初作者就指出现在CNN发展得很好,网络上像Facebook这一类... ...
Domain adaptationDiscriminative dictionary evolutionFeature representation learningTransfer learningThis work focuses on unsupervised visual domain adaptation which is still challenging in visual recognition. Most of the attention has been dedicated to seeking the domain-invariant features of cross-domain data, ...
In this paper, it is proved that dictionary learning and sparse representation is invariant to a linear transformation. It subsumes the special case of transforming/projecting the data into a discriminative space. This is important because recently, supervised dictionary learning algorithms have been pr...
判别字典学习Learning A Discriminative Dictionary for Sparse Representation
To address these problems, in this study, we propose a novel domain adaptation method, referred to as discriminative invariant alignment (DIA), for image representation. DIA enriches the knowledge matrix by combining the class discriminative information of the source domain and local data structure ...
To address this problem, horizontal shift-invariant transforms can be used in the watermarking design. Kim et al. [16] employ the DT-CWT to achieve approximate shift invariance in order to improve the robustness against DIBR conversion attacks, whereas Asikuzzaman et al. [3] propose a DT-...
The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data ...
{chench,zhchen,byjiang,jinxy}@zju.eduAbstractRecently,considerableefforthasbeendevotedtodeepdo-mainadaptationincomputervisionandmachinelearningcommunities.However,mostofexistingworkonlyconcen-tratesonlearningsharedfeaturerepresentationbyminimiz-ingthedistributiondiscrepancyacrossdifferentdomains.Duetothefactthatallthe...
Subsequently, each video clip is pooled as a histogram feature for activity representation. Lastly, we propose an orthogonal ensemble metric learning (OEML) method to learn a distance metric to exploit more discriminative information for recognition. Experimental results on five benchmark activity ...