W2WNet: a two-module probabilistic Convolutional Neural Network with embedded data cleansing functionality

TL;DR

W2WNet is a two-module CNN that uses Bayesian inference to identify and discard degraded or mislabeled images, improving classification accuracy especially in real-world, noisy datasets.

Contribution

The paper introduces W2WNet, a novel two-module CNN with embedded data cleansing using Bayesian inference, enhancing robustness against data degradation and mislabeling.

Findings

W2WNet effectively identifies degraded and mislabeled images.

Improves classification accuracy on benchmark datasets.

Demonstrates robustness in real-world histological image analysis.

Abstract

Convolutional Neural Networks (CNNs) are supposed to be fed with only high-quality annotated datasets. Nonetheless, in many real-world scenarios, such high quality is very hard to obtain, and datasets may be affected by any sort of image degradation and mislabelling issues. This negatively impacts the performance of standard CNNs, both during the training and the inference phase. To address this issue we propose Wise2WipedNet (W2WNet), a new two-module Convolutional Neural Network, where a Wise module exploits Bayesian inference to identify and discard spurious images during the training, and a Wiped module takes care of the final classification while broadcasting information on the prediction confidence at inference time. The goodness of our solution is demonstrated on a number of public benchmarks addressing different image classification tasks, as well as on a real-world case study on histological image analysis. Overall, our experiments demonstrate that W2WNet is able to identify image degradation and mislabelling issues both at training and at inference time, with a positive impact on the final classification accuracy.