Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
Christian Rupprecht,Christian Rupprecht,Iro Laina,Robert S. DiPietro,Maximilian Baust +4 more
- pp 3611-3620
Reads0
Chats0
TLDR
This work proposes a frame-work for reformulating existing single-prediction models as multiple hypothesis prediction (MHP) models and an associated meta loss and optimization procedure to train them, and finds that MHP models outperform their single-hypothesis counterparts in all cases and expose valuable insights into the variability of predictions.Abstract:
Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For example, in object detection, many objects of interest often go unlabeled, and in human pose estimation, occluded joints are often labeled with ambiguous values. In this work we focus on a principled approach for handling such scenarios. In particular, we propose a frame-work for reformulating existing single-prediction models as multiple hypothesis prediction (MHP) models and an associated meta loss and optimization procedure to train them. To demonstrate our approach, we consider four diverse applications: human pose estimation, future prediction, image classification and segmentation. We find that MHP models outperform their single-hypothesis counterparts in all cases, and that MHP models simultaneously expose valuable insights into the variability of predictions.read more
Citations
More filters
Proceedings ArticleDOI
Interpretable Social Anchors for Human Trajectory Forecasting in Crowds
TL;DR: In this article, the authors leverage the power of discrete choice models to learn interpretable rule-based intents, and subsequently utilize the expressibility of neural networks to model scene-specific residual.
Proceedings ArticleDOI
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
TL;DR: In this article, a multi-image shape and pose estimation method was proposed to predict body shape distributions from a group of multiple RGB images of a human subject without constraints on subject pose, camera viewpoint or background conditions between images in the group.
Posted Content
Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
TL;DR: This paper proposed a sampling-free approach for computing the epistemic uncertainty of a neural network, which does not require sampling at inference time and can reduce the computational overhead of estimation of the uncertainty.
Proceedings ArticleDOI
A Multi-Hypothesis Approach to Color Constancy
Daniel Hernandez-Juarez,Sarah Parisot,Benjamin Busam,Ales Leonardis,Gregory G. Slabaugh,Steven McDonagh +5 more
TL;DR: This work proposes a Bayesian framework that naturally handles color constancy ambiguity via a multi-hypothesis strategy and provides state-of-the-art accuracy on multiple public datasets (up to 11% median angular error improvement) while maintaining real-time execution.
Proceedings ArticleDOI
Video Relation Detection via Multiple Hypothesis Association
TL;DR: This paper proposes a novel relation association method called Multiple Hypothesis Association (MHA), which maintains multiple possible relation hypothesis during the association process in order to tolerate and handle the inaccurate or missing problem in the former steps and generate more accurate video relations.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.