Supplemental material for the paper “ Discriminative learning of Deep

Learning Discriminative Data Fitting Functions for Blind Image Deblurring Supplemental Material

Overview In this supplemental material, we give the derivation details of important equations of the main paper in Sections 1 and 2, Section 3 presents the algorithm details of the discriminative non-blind deconvolution. We demonstrate the flexibility of the proposed method in Section 4 and provide more experimental results of the proposed algorithm against the state-of-the-art deblurring metho...

Deep Learning for Tumor Classification in Imaging Mass Spectrometry - Supplemental Material

Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for “task oriented feature learning” grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. In this paper, we present a novel way of learning discriminative features by...

Supplemental Material for Photorealistic Facial Texture Inference Using Deep Neural Networks

Our main results in the paper demonstrate successful inference of high-fidelity texture maps from unconstrained images. The input images have mostly low resolutions, nonfrontal faces, and the subjects are often captured in challenging lighting conditions. We provide additional results with pictures from the annotated faces-in-the-wild (AFW) dataset [10] to further demonstrate how photorealistic...

Triplet-Center Loss for Multi-View 3D Object Retrieval

Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected. In the paper, we study variants of deep metric learning losses for 3D object retrieval, which did not rec...