DISCO Nets : DISsimilarity COefficients Networks

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training to the loss related to the task at hand. We empirically show that (i) by modeling uncertainty on the output value, DISCO Nets outperform equivalent non-probabilistic predictive networks and (ii) DISCO Nets accurately model the uncertainty of the output, outperforming existing probabilistic models based on deep neural networks.

• Publication year

  2016

• Venue

  Neural Information Processing Systems

• Publication date

  2016-06-08

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1606.02556
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative Adversarial Networks

  2021cited by this paper
• Generative Adversarial Text to Image Synthesis

  2016cited by this paper
• Generative Moment Matching Networks

  2015cited by this paper
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

  2015cited by this paper
• Conditional generative adversarial nets for convolutional face generation

  2015cited by this paper
• Adversarial Autoencoders

  2015cited by this paper
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

  2015cited by this paper
• Hands Deep in Deep Learning for Hand Pose Estimation

  2015influential reference
• Attribute2Image: Conditional Image Generation from Visual Attributes

  2015cited by this paper
• Training generative neural networks via Maximum Mean Discrepancy optimization

  2015cited by this paper
• Nonparametric Scoring Rules

  2015cited by this paper
• Training a Feedback Loop for Hand Pose Estimation

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015cited by this paper
• Empirical Minimum Bayes Risk Prediction: How to Extract an Extra Few % Performance from Vision Models with Just Three More Parameters

  2014cited by this paper
• Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks

  2014influential reference
• Strictly Proper Scoring Rules

  2014influential reference
• Conditional Generative Adversarial Nets

  2014cited by this paper
• Discrimination ability of the Energy score

  2013cited by this paper
• Auto-Encoding Variational Bayes

  2013cited by this paper
• Kernel Bayes' rule: Bayesian inference with positive definite kernels

  2013cited by this paper
• Modeling Latent Variable Uncertainty for Loss-based Learning

  2012cited by this paper
• A Kernel Two-Sample Test

  2012cited by this paper
• The Vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation

  2012cited by this paper
• Approximate inference for the loss-calibrated Bayesian

  2011cited by this paper
• Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds

  2008cited by this paper
• Strictly Proper Scoring Rules, Prediction, and Estimation

  2007cited by this paper
• A Kernel Method for the Two-Sample-Problem

  2006cited by this paper
• The Kernel Trick for Distances

  2000cited by this paper
• Diversity and dissimilarity coefficients: A unified approach☆

  1982cited by this paper
• Some methods of speeding up the convergence of iteration methods

  1964cited by this paper

• Exploring design space: Machine learning for multi-objective materials design optimization with enhanced evaluation strategies

  2025cites this paper
• Likelihood-Free Variational Autoencoders

  2025cites this paper
• Representation Learning for Extrapolation in Perturbation Modeling

  2025cites this paper
• Distributional Diffusion Models with Scoring Rules

  2025influential citation
• A Deep Learning Approach to Identifying Neural SDE Models Using the Signature Kernel

  2025cites this paper
• Learn to Guide Your Diffusion Model

  2025cites this paper
• Multivariate Uncertainty Quantification with Tomographic Quantile Forests

  2025cites this paper
• A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research

  2024cites this paper
• Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions

  2024cites this paper
• Non-adversarial training of Neural SDEs with signature kernel scores

  2023cites this paper
• Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning

  2023cites this paper
• Estimating Regression Predictive Distributions with Sample Networks

  2022cites this paper
• Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

  2022influential citation
• Likelihood-Free Inference with Generative Neural Networks via Scoring Rule Minimization

  2022cites this paper
• PEAN: 3D Hand Pose Estimation Adversarial Network

  2021cites this paper
• An enhanced self-attention and A2J approach for 3D hand pose estimation

  2021cites this paper
• Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors

  2021cites this paper
• Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization

  2021cites this paper
• Probabilistic Forecasting with Conditional Generative Networks via Scoring Rule Minimization

  2021cites this paper
• A CNN model for real time hand pose estimation

  2021cites this paper
• Survey of XAI in Digital Pathology

  2020cites this paper
• Artificial Intelligence and Machine Learning for Digital Pathology: State-of-the-Art and Future Challenges

  2020cites this paper
• 3D Hand Pose Estimation from Single Depth Images with Label Distribution Learning

  2020cites this paper
• A Survey on 3D Hand Skeleton and Pose Estimation by Convolutional Neural Network

  2020cites this paper
• Uncertainty modelling in deep learning for safer neuroimage enhancement: Demonstration in diffusion MRI

  2020cites this paper
• Improve Regression Network on Depth Hand Pose Estimation With Auxiliary Variable

  2020cites this paper
• Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations

  2020cites this paper
• A Spectral Energy Distance for Parallel Speech Synthesis

  2020cites this paper
• Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances

  2020cites this paper
• Generalized Feedback Loop for Joint Hand-Object Pose Estimation

  2019cites this paper
• Exploiting Negative Evidence for Deep Latent Structured Models

  2019cites this paper
• Adversarial-residual-coarse-graining: Applying machine learning theory to systematic molecular coarse-graining.

  2019cites this paper
• Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

  2019cites this paper
• Synthesizing Depth Hand Images with GANs and Style Transfer for Hand Pose Estimation

  2019cites this paper
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement

  2019cites this paper
• A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth Image

  2019influential citation
• Capturing Hand Articulations using Recurrent Neural Network for 3D Hand Pose Estimation

  2019cites this paper
• Demystifying MMD GANs

  2018influential citation
• Frequentist uncertainty estimates for deep learning

  2018cites this paper
• SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds

  2018cites this paper
• Braverman Readings in Machine Learning. Key Ideas from Inception to Current State: International Conference Commemorating the 40th Anniversary of Emmanuil Braverman's Decease, Boston, MA, USA, April 28-30, 2017, Invited Talks

  2018cites this paper
• Learning Human Poses from Actions-Supplementary Material

  2018influential citation
• Learning Human Poses from Actions

  2018influential citation
• A Probabilistic U-Net for Segmentation of Ambiguous Images

  2018cites this paper
• Lightweight Probabilistic Deep Networks

  2018cites this paper
• Lightweight Probabilistic Deep Networks

  2018cites this paper
• Deep Directional Statistics: Pose Estimation with Uncertainty Quantification

  2018cites this paper
• Cross-Modal Deep Variational Hand Pose Estimation

  2018cites this paper
• Single-Model Uncertainties for Deep Learning

  2018cites this paper
• Dissimilarity Coefficient Based Weakly Supervised Object Detection

  2018influential citation
• MURAUER: Mapping Unlabeled Real Data for Label AUstERity

  2018cites this paper
• Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems

  2018cites this paper
• Task-oriented learning of structured probability distributions

  2017influential citation
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations

  2017cites this paper
• DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

  2017cites this paper
• Geometrical Insights for Implicit Generative Modeling

  2017influential citation
• Stabilizing Training of Generative Adversarial Networks through Regularization

  2017cites this paper
• V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

  2017influential citation
• Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images

  2017cites this paper
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning

  2017cites this paper
• Kernel Mean Embedding of Distributions: A Review and Beyonds

  2016cites this paper
• Adversarial Message Passing For Graphical Models

  2016cites this paper
• Hand pose estimation through semi-supervised and weakly-supervised learning

  2015cites this paper