Uncertainty Class Activation Map (U-CAM) Using Gradient Certainty Method
| Autor: | Vinay P. Namboodiri, Mayank Lunayach, Badri N. Patro |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
visual question answering
Computer science Aleatoric epistemic uncertainty media_common.quotation_subject 02 engineering and technology Machine learning computer.software_genre Task (project management) Knowledge extraction Artificial Intelligence Image Processing Computer-Assisted 0202 electrical engineering electronic engineering information engineering Question answering Humans media_common Class (computer programming) business.industry Deep learning class activation map Uncertainty Probabilistic logic Bayes Theorem Certainty Computer Graphics and Computer-Aided Design attention Visualization Bayesian model Task analysis 020201 artificial intelligence & image processing Artificial intelligence LSTM explanation business computer CNN Algorithms Software |
| Zdroj: | Patro, B, Lunayach, M & Namboodiri, V 2021, ' Uncertainty Class Activation Map (U-CAM) using Gradient Certainty method ', IEEE Transactions on Image Processing, vol. 30, pp. 1910-1924 . https://doi.org/10.1109/TIP.2020.3046916 |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2020.3046916 |
| Popis: | Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question answering task. We incorporate modern probabilistic deep learning methods that we further improve by using the gradients for these estimates. These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions. The improved attention maps result in consistent improvement for various methods for visual question answering. Therefore, the proposed technique can be thought of as a tool for obtaining improved certainty estimates and explanations for deep learning models. We provide detailed empirical analysis for the visual question answering task on all standard benchmarks and comparison with state of the art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|