DeepAI AI Chat
Log In Sign Up

A Method for Restoring the Training Set Distribution in an Image Classifier

by   Alexey Chaplygin, et al.

Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation set, but can easily be fooled by data that is specifically generated for the purpose. It has been shown that one can produce an artificial example that does not represent the desired class, but activates the network in the desired way. This paper describes a new way of reconstructing a sample from the training set distribution of an image classifier without deep knowledge about the underlying distribution. This enables access to the elements of images that most influence the decision of a convolutional network and to extract meaningful information about the training distribution.


page 2

page 3

page 4

page 5

page 6

page 7

page 8


Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output

Deep neural networks achieve superior performance in challenging tasks s...

An Algorithm to Attack Neural Network Encoder-based Out-Of-Distribution Sample Detector

Deep neural network (DNN), especially convolutional neural network, has ...

Boosting Deep Hyperspectral Image Classification with Spectral Unmixing

Recent advances in neural networks have made great progress in addressin...

Prototypical Classifier for Robust Class-Imbalanced Learning

Deep neural networks have been shown to be very powerful methods for man...

Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis

Dermoscopic skin images are often obtained with different imaging device...

Convolutional Neural Networks for Aerial Vehicle Detection and Recognition

This paper investigates the problem of aerial vehicle recognition using ...

Over-parameterization: A Necessary Condition for Models that Extrapolate

In this work, we study over-parameterization as a necessary condition fo...