Sort by: Year Popularity Relevance

DC-WCNN: A deep cascade of wavelet based convolutional neural networks for MR Image Reconstruction

, , ,  - 2020

Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. However, sub-sampling is performed by its pooling layers, causing information loss which in turn leads to blur and missing fine detai...


Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

, ,  - 2020

CT scanners that are commonly-used in hospitals nowadays produce low-resolution images, up to 512 pixels in size. One pixel in the image corresponds to a one millimeter piece of tissue. In order to accurately segment tumors and make treatment plans, doctors need CT scans of higher resolution. The same problem appears in MRI. In this paper, we pro...


A Deep Learning Approach for the Computation of Curvature in the Level-Set Method

,  - 2020

We propose a deep learning strategy to compute the mean curvature of an implicit level-set representation of an interface. Our approach is based on fitting neural networks to synthetic datasets of pairs of nodal $\phi$ values and curvatures obtained from circular interfaces immersed in different uniform resolutions. These neural networks are mult...


Evaluating Weakly Supervised Object Localization Methods Right

, , , , ,  - 2020

Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal WSOL work of class activation mapping (CAM), the field has focused on how to expand the attention regions to cover objects more broadly and localize them better. Howeve...


Object Instance Mining for Weakly Supervised Object Detection

, , , ,  - 2020

Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years. Existing approaches using multiple instance learning easily fall into local optima, because such mechanism tends to learn from the most discriminative object in an image for each category. Therefore, these methods ...


R2DE: a NLP approach to estimating IRT parameters of newly generated questions

, , ,  - 2020

The main objective of exams consists in performing an assessment of students' expertise on a specific subject. Such expertise, also referred to as skill or knowledge level, can then be leveraged in different ways (e.g., to assign a grade to the students, to understand whether a student might need some support, etc.). Similarly, the questions appe...


Adaptive Parameterization for Neural Dialogue Generation

, , , , ,  - 2020

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic re...


Learning Diverse Features with Part-Level Resolution for Person Re-Identification

, , , ,  - 2020

Learning diverse features is key to the success of person re-identification. Various part-based methods have been extensively proposed for learning local representations, which, however, are still inferior to the best-performing methods for person re-identification. This paper proposes to construct a strong lightweight network architecture, terme...


A Branching and Merging Convolutional Network with Homogeneous Filter Capsules

, ,  - 2020

We present a convolutional neural network design with additional branches after certain convolutions so that we can extract features with differing effective receptive fields and levels of abstraction. From each branch, we transform each of the final filters into a pair of homogeneous vector capsules. As the capsules are formed from entire filter...


Harmonic Convolutional Networks based on Discrete Cosine Transform

, ,  - 2020

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In this paper we propose to revert to learning combinations of preset spectral filters by switching to CNNs with harmonic blocks. We rely on the use of the Discrete Cosine Transform (DCT) filters which have excellent energy compacti...