Escaping Plato’s Cave: 3D Shape From Adversarial Rendering. (arXiv:1811.11606v3 [cs.CV] UPDATED)

We introduce PlatonicGAN to discover the 3D structure of an object class from an unstructured collection of 2D images, i.e., where no relation between photos is known, except that they are showing instances of the same category. The key idea is to train a deep neural network to generate 3D shapes which, when rendered to…

Topological Map Extraction from Overhead Images. (arXiv:1812.01497v3 [cs.CV] UPDATED)

We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly. PolyMapper directly extracts the topological map of a city from overhead images as collections of building footprints and road networks. In order to unify the shape representation for different types of…

Face Completion with Semantic Knowledge and Collaborative Adversarial Learning. (arXiv:1812.03252v2 [cs.CV] UPDATED)

Unlike a conventional background inpainting approach that infers a missing area from image patches similar to the background, face completion requires semantic knowledge about the target object for realistic outputs. Current image inpainting approaches utilize generative adversarial networks (GANs) to achieve such semantic understanding. However, in adversarial learning, the semantic knowledge is learned implicitly and…

More Knowledge is Better: Cross-Modality Volume Completion and 3D+2D Segmentation for Intracardiac Echocardiography Contouring. (arXiv:1812.03507v2 [cs.CV] UPDATED)

Using catheter ablation to treat atrial fibrillation increasingly relies on intracardiac echocardiography (ICE) for an anatomical delineation of the left atrium and the pulmonary veins that enter the atrium. However, it is a challenge to build an automatic contouring algorithm because ICE is noisy and provides only a limited 2D view of the 3D anatomy.…

Skin Disease Classification versus Skin Lesion Characterization: Achieving Robust Diagnosis using Multi-label Deep Neural Networks. (arXiv:1812.03520v2 [cs.CV] UPDATED)

In this study, we investigate what a practically useful approach is in order to achieve robust skin disease diagnosis. A direct approach is to target the ground truth diagnosis labels, while an alternative approach instead focuses on determining skin lesion characteristics that are more visually consistent and discernible. We argue that, for computer-aided skin disease…

Unsupervised Neural Mask Estimator For Generalized Eigen-Value Beamforming Based ASR. (arXiv:1911.12617v1 [eess.AS])

The state-of-art methods for acoustic beamforming in multi-channel ASR are based on a neural mask estimator that predicts the presence of speech and noise. These models are trained using a paired corpus of clean and noisy recordings (teacher model). In this paper, we attempt to move away from the requirements of having supervised clean recordings…

Machine learning for music genre: multifaceted review and experimentation with audioset. (arXiv:1911.12618v1 [cs.SD])

Music genre classification is one of the sub-disciplines of music information retrieval (MIR) with growing popularity among researchers, mainly due to the already open challenges. Although research has been prolific in terms of number of published works, the topic still suffers from a problem in its foundations: there is no clear and formal definition of…

Estimation of Blood Glucose Level of Type-2 Diabetes Patients using Smartphone Video. (arXiv:1911.12619v1 [eess.SP])

This work proposes a smartphone video-based approach for the estimation of blood glucose in a non-invasive way. Videos using smartphone camera are collected from the tip of the subjects finger and the frames are subsequently converted into Photoplethysmography (PPG) waveform. Gaussian filter along with Asymmetric Least Square methods have been applied on the PPG signals…

Learning restrictions on admissible switching signals for switched systems. (arXiv:1911.12635v1 [eess.SY])

The knowledge of restrictions on the set of admissible switching signals is important for the design of control strategies for switched systems. We propose an algorithm that learns these restrictions by collecting data from a gray-box simulation model of the switched system. Our learning technique is a modified version of the well-known L*-algorithm from machine…

Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization. (arXiv:1911.12574v1 [cs.LG])

Model-based reinforcement learning algorithms tend to achieve higher sample efficiency than model-free methods. However, due to the inevitable errors of learned models, model-based methods struggle to achieve the same asymptotic performance as model-free methods. In this paper, We propose a Policy Optimization method with Model-Based Uncertainty (POMBU)—a novel model-based approach—that can effectively improve the asymptotic…