VisualBackProp for learning using privileged information with CNNs

by   Devansh Bisla, et al.

In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of learning algorithms and incorporate `physical,' `domain knowledge,' or `common sense' concepts into training of machine learning systems as well as verify constraints/properties of the systems. We explore the learning using privileged information paradigm and show how to incorporate the privileged information, such as segmentation mask available along with the classification label of each example, into the training stage of convolutional neural networks. This is done by augmenting the CNN model with an architectural component that effectively focuses model's attention on the desired region of the input image during the training process and that is transparent to the network's label prediction mechanism at testing. This component effectively corresponds to the visualization strategy for identifying the parts of the input, often referred to as visualization mask, that most contribute to the prediction, yet uses this strategy in reverse to the classical setting in order to enforce the desired visualization mask instead. We verify our proposed algorithms through exhaustive experiments on benchmark ImageNet and PASCAL VOC data sets and achieve improvements in the performance of 2.4% and 2.7% over standard single-supervision model training. Finally, we confirm the effectiveness of our approach on skin lesion classification problem.


page 5

page 6

page 8


Skin lesion segmentation and classification using deep learning and handcrafted features

Accurate diagnostics of a skin lesion is a critical task in classificati...

Learning Using Privileged Information: SVM+ and Weighted SVM

Prior knowledge can be used to improve predictive performance of learnin...

Label-Free Supervision of Neural Networks with Physics and Domain Knowledge

In many machine learning applications, labeled data is scarce and obtain...

A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during training

Deep learning has outperformed other machine learning algorithms in a va...

Machine Learning using the Variational Predictive Information Bottleneck with a Validation Set

Zellner (1988) modeled statistical inference in terms of information pro...

VisualBackProp: efficient visualization of CNNs

This paper proposes a new method, that we call VisualBackProp, for visua...

Please sign up or login with your details

Forgot password? Click here to reset