CNN fixations : an unraveling approach to visualize the discriminative image regions
Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as bl...
Main Authors: | Mopuri, Konda Reddy, Garg, Utsav, Babu, R. Venkatesh |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/142317 |
Similar Items
-
TS-CNN: A Three-Tier Self-Interpretable CNN for Multi-Region Medical Image Classification
by: V. A. Ashwath, et al.
Published: (2023-01-01) -
Cardiovascular disease identification using a hybrid CNN-LSTM model with explainable AI
by: Md Maruf Hossain, et al.
Published: (2023-01-01) -
Visual Interpretation of CNN Prediction Through Layerwise Sequential Selection of Discernible Neurons
by: Md. Tauhid Bin Iqbal, et al.
Published: (2022-01-01) -
The Visual Analytics and Data Exploration Research Lab at Arizona State University
by: Ross Maciejewski, et al.
Published: (2021-03-01) -
ATICVis: A Visual Analytics System for Asymmetric Transformer Models Interpretation and Comparison
by: Jian-Lin Wu, et al.
Published: (2023-01-01)