Towards Analyzing Semantic Robustness of Deep Neural Networks

@inproceedings{Hamdi2020TowardsAS,
  title={Towards Analyzing Semantic Robustness of Deep Neural Networks},
  author={Abdullah Hamdi and Bernard Ghanem},
  booktitle={ECCV Workshops},
  year={2020}
}
Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high sensitivity toward semantic primitives (e.g. object pose). We propose a theoretically grounded analysis for DNN robustness in the semantic space. We qualitatively analyze different DNNs' semantic robustness by visualizing the DNN global behavior as semantic maps and observe interesting behavior of some DNNs. Since generating these semantic maps does not scale well with… Expand
Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations
3DB: A Framework for Debugging Computer Vision Models
Performance Evaluation of Various ANN Architectures Using Proposed Cost Function
  • Sandhya, Udayan Ghose, Upasana Bisht
  • Computer Science
  • 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)
  • 2020

References

SHOWING 1-10 OF 46 REFERENCES
The Robustness of Deep Networks: A Geometrical Perspective
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Intriguing properties of neural networks
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Rethinking the Inception Architecture for Computer Vision
Deep Residual Learning for Image Recognition
Understanding deep image representations by inverting them
Semantic Adversarial Examples
...
1
2
3
4
5
...