Open AccessPosted Content
Contextual Prediction Difference Analysis for Explaining Individual Image Classifications
Jindong Gu,Volker Tresp +1 more
TL;DR: This work first shows that PDA can suffer from saturated classifiers, then proposes Contextual PDA, which runs hundreds of times faster than PDA and is shown to be superior by explaining image classifications of the state-of-the-art deep convolutional neural networks.
read more
Abstract: Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However, they are not applicable when the parameters and the gradients of the underlying models are unavailable. Recently, model-agnostic methods have also received attention. As one of them, \textit{Prediction Difference Analysis} (PDA), a probabilistic sound methodology, was proposed. In this work, we first show that PDA can suffer from saturated classifiers. The saturation phenomenon of classifiers exists widely in current neural network-based classifiers. To explain the decisions of saturated classifiers better, we further propose Contextual PDA, which runs hundreds of times faster than PDA. The experiments show the superiority of our method by explaining image classifications of the state-of-the-art deep convolutional neural networks.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Wojciech Samek,Grégoire Montavon,Sebastian Lapuschkin,Christopher J. Anders,Klaus-Robert Müller +4 more
TL;DR: In this paper, the authors provide a timely overview of explainable AI, with a focus on 'post-hoc' explanations, explain its theoretical foundations, and put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations.
709
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Wojciech Samek,Grégoire Montavon,Sebastian Lapuschkin,Christopher J. Anders,Klaus-Robert Müller +4 more
- 04 Mar 2021
TL;DR: In this paper, the authors provide a timely overview of post hoc explanations and explain its theoretical foundations, and put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations, and demonstrate successful usage of XAI in a representative selection of application scenarios.
•Posted Content
Shapley-based explainability on the data manifold.
Christopher Frye,Damien de Mijolla,Laurence Cowton,Megan Stanley,Ilya Feige +4 more
- 01 Jun 2020
TL;DR: This work articulate the dangers of this assumption and introduces two solutions for computing Shapley explanations that respect the data manifold, which provides flexible access to on-manifold data imputations and directly learns the Shapley value function in a supervised way, providing performance and stability at the cost of flexibility.
28
Neural Network Predicts Need for Red Blood Cell Transfusion for Patients with Acute Gastrointestinal Bleeding Admitted to the Intensive Care Unit
Dennis Shung,Egbert Castro,Jessie Huang,J. Kenneth Tay,Michael Simonov,Loren Laine,Smita Krishnaswamy +6 more
TL;DR: A long short-term memory (LSTM) model can be used to predict the need for transfusion of packed red blood cells over the first 24 hours from admission to help personalize the care of high-risk patients with acute gastrointestinal bleeding.
Prediction Difference Regularization against Perturbation for Neural Machine Translation
Dengji Guo,Zhengrui Ma,Jinghui Zhang,Yang Feng +3 more
- 01 Jan 2022
TL;DR: This paper utilizes prediction difference for ground-truth tokens to analyze the fitting of token-level samples and finds that under-fitting is almost as common as over-fitting, so prediction difference regularization (PD-R) is introduced, a simple and effective method that can reduce over- fitting and under- fitting at the same time.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
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.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.