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
Posted Content
Deep Context-Aware Novelty Detection.
Ellen Rushe,Brian Mac Namee +1 more
TL;DR: A context-aware approach to novelty detection for deep autoencoders is proposed which utilises auxiliary labels in order to reveal contextual information and allows the model to adapt to a variety of normal and novel scenarios.
Journal ArticleDOI
Application of belief functions to medical image segmentation: A review
Ling-Wei Huang,Su Ruan +1 more
TL;DR: In this paper , the authors provide an introduction to the topic of medical image segmentation methods using belief function theory, and classify the methods according to the fusion step and explain how information with uncertainty or imprecision is modeled and fused with belief function theories.
Posted Content
Anomaly Detection in Particulate Matter Sensor using Hypothesis Pruning Generative Adversarial Network.
TL;DR: A novel architecture named with Hypothesis Pruning Generative Adversarial Network (HP-GAN) for anomaly detection is proposed and the results show that proposed architecture achieves cutting-edge performance at anomaly detection.
Proceedings ArticleDOI
A Probabilistic Model for Controlling Diversity and Accuracy of Ambiguous Medical Image Segmentation
TL;DR: A novel probabilistic segmentation model, called Joint Probabilistic U-net, is proposed, which successfully achieves flexible control over the two abstract conceptions of diversity and accuracy, and two strategies for preventing the latent space collapse are explored.
Proceedings ArticleDOI
Learn the Highest Label and Rest Label Description Degrees
Jing Wang,Xin Geng +1 more
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.