Search Results - "R T, Akash Guna"
-
1
Ante-Hoc Generation of Task-Agnostic Interpretation Maps
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2023)“…Existing explainability approaches for convolutional neural networks (CNNs) are mainly applied after training (post-hoc) which is generally unreliable…”
Get full text
Conference Proceeding -
2
Interpreting CNN predictions using conditional Generative Adversarial Networks
Published in Knowledge-based systems (25-10-2024)“…We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual explanations of a Convolutional Neural Network…”
Get full text
Journal Article -
3
Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures
Published 19-02-2024“…Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by…”
Get full text
Journal Article -
4
Interpreting CNN Predictions using Conditional Generative Adversarial Networks
Published 19-01-2023“…We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network…”
Get full text
Journal Article