English

A Step Towards Exposing Bias in Trained Deep Convolutional Neural Network Models

Computer Vision and Pattern Recognition 2019-12-05 v1

Abstract

We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance. We experimented with few images, and we discovered that Smooth Grad-CAM++ produced more visually sharp maps with larger number of salient pixels highlighted in the given input images when compared with other methods. Smooth Grad-CAM++ will give insight into what our deep CNN models (including models trained on medical scan or imagery) learn. Hence informing decisions on creating a representative training set.

Keywords

Cite

@article{arxiv.1912.02094,
  title  = {A Step Towards Exposing Bias in Trained Deep Convolutional Neural Network Models},
  author = {Daniel Omeiza},
  journal= {arXiv preprint arXiv:1912.02094},
  year   = {2019}
}

Comments

Presented at NeurIPS 2019 Workshop on Machine Learning for the Developing World. arXiv admin note: substantial text overlap with arXiv:1908.01224

R2 v1 2026-06-23T12:35:51.960Z