M
Mahesh Sudhakar
Researcher at University of Toronto
Publications - 6
Citations - 57
Mahesh Sudhakar is an academic researcher from University of Toronto. The author has contributed to research in topics: Convolutional neural network & Backpropagation. The author has an hindex of 2, co-authored 6 publications receiving 9 citations.
Papers
More filters
Proceedings ArticleDOI
Integrated Grad-Cam: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks Via Integrated Gradient-Based Scoring
Sam Sattarzadeh,Mahesh Sudhakar,Konstantinos N. Plataniotis,Jongseong Jang,Yeonjeong Jeong,Hyunwoo Kim +5 more
TL;DR: In this article, the path integral of the gradient-based terms in Grad-CAM is computed to measure the importance of the extracted representations for the CNNs predictions, which yields to the method's administration in object localization and model interpretation.
Posted Content
Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation
Sam Sattarzadeh,Mahesh Sudhakar,Anthony Lem,Shervin Mehryar,Konstantinos N. Plataniotis,Jongseong Jang,Hyunwoo Kim,Yeonjeong Jeong,Sangmin Lee,Kyunghoon Bae +9 more
TL;DR: This work collects visualization maps from multiple layers of the model based on an attribution-based input sampling technique and aggregate them to reach a fine-grained and complete explanation, and proposes a layer selection strategy that applies to the whole family of CNN-based models.
Proceedings ArticleDOI
Ada-Sise: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
Mahesh Sudhakar,Sam Sattarzadeh,Konstantinos N. Plataniotis,Jongseong Jang,Yeonjeong Jeong,Hyunwoo Kim +5 more
TL;DR: Zhang et al. as discussed by the authors combine perturbation-based model analysis and backpropagation techniques as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks.
Proceedings ArticleDOI
SVEA: A Small-Scale Benchmark for Validating the Usability of Post-Hoc Explainable AI Solutions in Image and Signal Recognition
Posted Content
Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
Sam Sattarzadeh,Mahesh Sudhakar,Konstantinos N. Plataniotis,Jongseong Jang,Yeonjeong Jeong,Hyunwoo Kim +5 more
TL;DR: In this article, the path integral of the gradient-based terms in Grad-CAM is computed to measure the importance of the extracted representations for the CNN's predictions, which yields to their administration in object localization and model interpretation.