Book Chapter10.1007/978-3-030-77964-1_33
Automated Method for Evaluating Neural Network's Attention Focus.
Tomasz Szandała,Henryk Maciejewski +1 more
- 16 Jun 2021
- pp 426-436
2
TL;DR: In this paper, the authors identify the threat of network incorrectly relying on counterfactual features that can stay undetectable during validation but cause serious issues in life application and propose a method to counter this hazard.
read more
Abstract: Rapid progress in machine learning and artificial intelligence (AI) has brought increased attention to the potential security and reliability of AI technologies. This paper identifies the threat of network incorrectly relying on counterfactual features that can stay undetectable during validation but cause serious issues in life application. Furthermore, we propose a method to counter this hazard. It combines well-known techniques: object detection tool and saliency map obtaining formula to compute metric indicating potentially faulty learning. We prove the effectiveness of the method, as well as discuss its shortcomings.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation
TL;DR: Gradual Extrapolation as discussed by the authors is an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation to present the visual explanations of decisions from convolutional neural network-based models.
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Anh Nguyen,Jason Yosinski,Jeff Clune +2 more
- 07 Jun 2015
TL;DR: In this article, the authors show that it is possible to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence.