
Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks
In the past few years, deep learning has transformed artificial intellig...
read it

Finegrained Recognition: Accounting for Subtle Differences between Similar Classes
The main requisite for finegrained recognition task is to focus on subt...
read it

(1 + ε)class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets
Anomaly detection is not an easy problem since distribution of anomalous...
read it

NoRegret Learning in Unknown Games with Correlated Payoffs
We consider the problem of learning to play a repeated multiagent game ...
read it

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
In this paper, we consider the problem of reconstructing a dense 3D mode...
read it

An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information: Exponential Decay vs. Full Preservation
Graph Convolutional Network (GCN) has attracted intensive interests rece...
read it

Noregret Bayesian Optimization with Unknown Hyperparameters
Bayesian optimization (BO) based on Gaussian process models is a powerfu...
read it

Active Learning for Segmentation Based on Bayesian Sample Queries
Segmentation of anatomical structures is a fundamental image analysis ta...
read it

Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Evolutionary Strategies (ES) are known to be an effective blackbox opti...
read it

EVIMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras
We present the first eventbased learning approach for motion segmentati...
read it

This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
There has been a remarkable progress in the accuracy of semantic segment...
read it

Wavelet Domain Style Transfer for an Effective Perceptiondistortion Tradeoff in Single Image SuperResolution
In single image superresolution (SISR), given a lowresolution (LR) ima...
read it

Efficient Video Semantic Segmentation with Labels Propagation and Refinement
This paper tackles the problem of realtime semantic segmentation of hig...
read it

Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene
This work addresses the task of dense 3D reconstruction of a complex dyn...
read it

InformationDirected Exploration for Deep Reinforcement Learning
Efficient exploration remains a major challenge for reinforcement learni...
read it

Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations
The goal of many computer vision systems is to transform image pixels in...
read it

GLAMpoints: Greedily Learned Accurate Match points
We introduce a novel CNNbased feature point detector  GLAMpoints  lea...
read it

Meta Answering for Machine Reading
We investigate a framework for machine reading, inspired by real world i...
read it

AI Benchmark: Running Deep Neural Networks on Android Smartphones
Over the last years, the computational power of mobile devices such as s...
read it

Interventional Robustness of Deep Latent Variable Models
The ability to learn disentangled representations that split underlying ...
read it

SMIT: Stochastic MultiLabel ImagetoImage Translation
Crossdomain mapping has been a very active topic in recent years. Given...
read it

An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms
This paper focuses on valuating training data for supervised learning ta...
read it

Selfsupervised Object Motion and Depth Estimation from Video
We present a selfsupervised learning framework to estimate the individu...
read it

KnowledgeInduced Learning with Adaptive Sampling Variational Autoencoders for Open Set Fault Diagnostics
The recent increase in the availability of system condition monitoring d...
read it

Extremely Weak Supervised ImagetoImage Translation for Semantic Segmentation
Recent advances in generative models and adversarial training have led t...
read it

DLOW: Domain Flow for Adaptation and Generalization
In this work, we propose a domain flow generation(DLOW) approach to mode...
read it

AReS and MaRS  Adversarial and MMDMinimizing Regression for SDEs
Stochastic differential equations are an important modeling class in man...
read it

Adversarial Training Generalizes Datadependent Spectral Norm Regularization
We establish a theoretical link between adversarial training and operato...
read it

Learning Filter Basis for Convolutional Neural Network Compression
Convolutional neural networks (CNNs) based solutions have achieved state...
read it

AIM 2019 Challenge on RealWorld Image SuperResolution: Methods and Results
This paper reviews the AIM 2019 challenge on real world superresolution...
read it

EBPC: Extended BitPlane Compression for Deep Neural Network Inference and Training Accelerators
In the wake of the success of convolutional neural networks in image cla...
read it

HistoNet: Predicting size histograms of object instances
We propose to predict histograms of object sizes in crowded scenes direc...
read it

XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference
Binary Neural Networks (BNNs) are promising to deliver accuracy comparab...
read it

Realtime 3D Traffic Cone Detection for Autonomous Driving
Considerable progress has been made in semantic scene understanding of r...
read it

ODIN: ODEInformed Regression for Parameter and State Inference in TimeContinuous Dynamical Systems
Parameter inference in ordinary differential equations is an important p...
read it

Learning ContentWeighted Deep Image Compression
Learningbased lossy image compression usually involves the joint optimi...
read it

An Efficient Samplingbased Method for Online Informative Path Planning in Unknown Environments
The ability to plan informative paths online is essential to robot auton...
read it

Oracle inequalities for image denoising with total variation regularization
We derive oracle results for discrete image denoising with a total varia...
read it

Domain Agnostic Feature Learning for Image and Video Based Face Antispoofing
Nowadays, the increasingly growing number of mobile and computing device...
read it

3D Appearance SuperResolution with Deep Learning
We tackle the problem of retrieving highresolution (HR) texture maps of...
read it

Targetless registration of point clouds: A review
Point cloud registration has been one of the basic steps of point cloud ...
read it

MTINet: MultiScale Task Interaction Networks for MultiTask Learning
In this paper, we highlight the importance of considering task interacti...
read it

Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided InputOutput Adaptation Approach
Recently, increasing attention has been drawn to training semantic segme...
read it

Neural Sequential Phrase Grounding (SeqGROUND)
We propose an endtoend approach for phrase grounding in images. Unlike...
read it

PIRM2018 Challenge on Spectral Image SuperResolution: Dataset and Study
This paper introduces a newly collected and novel dataset (StereoMSI) fo...
read it

Simultaneous multiview instance detection with learned geometric softconstraints
We propose to jointly learn multiview geometry and warping between view...
read it

Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences
Predicting the remaining useful life of machinery, infrastructure, or ot...
read it

Semantic Understanding of Foggy Scenes with Purely Synthetic Data
This work addresses the problem of semantic scene understanding under fo...
read it

Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of B
The development of new classification and regression algorithms based on...
read it

Practical Full Resolution Learned Lossless Image Compression
We propose the first practical learned lossless image compression system...
read it
ETH Zurich
ETH Zurich is a science, technology, engineering and mathematics university in the city of Zürich, Switzerland.