Valid P-Value for Deep Learning-Driven Salient Region
- URL: http://arxiv.org/abs/2301.02437v1
- Date: Fri, 6 Jan 2023 09:51:09 GMT
- Title: Valid P-Value for Deep Learning-Driven Salient Region
- Authors: Daiki Miwa, Vo Nguyen Le Duy, Ichiro Takeuchi
- Abstract summary: We propose a method to quantify the reliability of a salient region in the form of p-values.
The proposed method can provably control the probability of false positive detections of salient regions.
- Score: 21.184555512370085
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Various saliency map methods have been proposed to interpret and explain
predictions of deep learning models. Saliency maps allow us to interpret which
parts of the input signals have a strong influence on the prediction results.
However, since a saliency map is obtained by complex computations in deep
learning models, it is often difficult to know how reliable the saliency map
itself is. In this study, we propose a method to quantify the reliability of a
salient region in the form of p-values. Our idea is to consider a salient
region as a selected hypothesis by the trained deep learning model and employ
the selective inference framework. The proposed method can provably control the
probability of false positive detections of salient regions. We demonstrate the
validity of the proposed method through numerical examples in synthetic and
real datasets. Furthermore, we develop a Keras-based framework for conducting
the proposed selective inference for a wide class of CNNs without additional
implementation cost.
Related papers
- Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data.
One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is.
This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
arXiv Detail & Related papers (2024-01-18T08:12:23Z) - Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
We show that the gradient of a model is a special case of a more general formulation using semirings.
This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
arXiv Detail & Related papers (2023-07-06T15:19:53Z) - Uncertainty Quantification in Deep Neural Networks through Statistical
Inference on Latent Space [0.0]
We develop an algorithm that exploits the latent-space representation of data points fed into the network to assess the accuracy of their prediction.
We show on a synthetic dataset that commonly used methods are mostly overconfident.
In contrast, our method can detect such out-of-distribution data points as inaccurately predicted, thus aiding in the automatic detection of outliers.
arXiv Detail & Related papers (2023-05-18T09:52:06Z) - STEERING: Stein Information Directed Exploration for Model-Based
Reinforcement Learning [111.75423966239092]
We propose an exploration incentive in terms of the integral probability metric (IPM) between a current estimate of the transition model and the unknown optimal.
Based on KSD, we develop a novel algorithm algo: textbfSTEin information dirtextbfEcted exploration for model-based textbfReinforcement LearntextbfING.
arXiv Detail & Related papers (2023-01-28T00:49:28Z) - Bayesian Graph Contrastive Learning [55.36652660268726]
We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders.
Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector.
We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
arXiv Detail & Related papers (2021-12-15T01:45:32Z) - A Variational Bayesian Approach to Learning Latent Variables for
Acoustic Knowledge Transfer [55.20627066525205]
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models.
Our proposed VB approach can obtain good improvements on target devices, and consistently outperforms 13 state-of-the-art knowledge transfer algorithms.
arXiv Detail & Related papers (2021-10-16T15:54:01Z) - Instance-Based Neural Dependency Parsing [56.63500180843504]
We develop neural models that possess an interpretable inference process for dependency parsing.
Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set.
arXiv Detail & Related papers (2021-09-28T05:30:52Z) - Building Reliable Explanations of Unreliable Neural Networks: Locally
Smoothing Perspective of Model Interpretation [0.0]
We present a novel method for reliably explaining the predictions of neural networks.
Our method is built on top of the assumption of smooth landscape in a loss function of the model prediction.
arXiv Detail & Related papers (2021-03-26T08:52:11Z) - BDNNSurv: Bayesian deep neural networks for survival analysis using
pseudo values [7.707091943385522]
We propose a Bayesian hierarchical deep neural networks model for modeling and prediction of survival data.
Compared with previously studied methods, the new proposal can provide point estimate of survival probability.
The Python code implementing the proposed approach was provided.
arXiv Detail & Related papers (2021-01-07T20:18:43Z) - Ramifications of Approximate Posterior Inference for Bayesian Deep
Learning in Adversarial and Out-of-Distribution Settings [7.476901945542385]
We show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks.
Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions.
arXiv Detail & Related papers (2020-09-03T16:58:15Z) - A generalizable saliency map-based interpretation of model outcome [1.14219428942199]
We propose a non-intrusive interpretability technique that uses the input and output of the model to generate a saliency map.
Experiments show that our interpretability method can reconstruct the salient part of the input with a classification accuracy of 89%.
arXiv Detail & Related papers (2020-06-16T20:34:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.