11 citations · 21 across the 5 of their papers we have counts for
11 papers
Informative Class Activation Maps
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
We study how to evaluate the quantitative information content of a region within an image for a particular label. To this end, we bridge class activation maps with information theo…
Neural Network Classifier as Mutual Information Evaluator
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as…
Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
Yang Liu, Saeed Anwar, Zhenyue Qin +3
The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. Howe…
Invertible Denoising Network: A Light Solution for Real Noise Removal
Yang Liu, Zhenyue Qin, Saeed Anwar +4
Invertible networks have various benefits for image denoising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying inverti…
Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable
Yang Liu, Zhenyue Qin, Saeed Anwar +2
Ever since the advent of AlexNet, designing novel deep neural architectures for different tasks has consistently been a productive research direction. Despite the exceptional perfo…
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We sho…