Quality Resilient Deep Neural Networks
By Samuel F. Dodge, Lina Karam. 2017
47 citations recorded by the source corpus.
We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned networks perform poorly on quality distortions that they have not been trained for. We propose a mixture of experts ensemble method that is robust to different types of distortions. The "experts" in our model are trained on a particular type of distortion. The output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The gating network is trained to predict optimal weights for a particular distortion type and level. During testing, the network is blind to the distortion level and type, yet can still assign appropriate weights to the expert models. We additionally investigate weight sharing methods for the mixture model and show that improved performance can be achieved with a large reduction in the number of unique network parameters.
Subfields: Computer Vision and Pattern Recognition, Media Technology, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Wieland Brendel
- Matthias Bethge
- Luc Van Gool
- Dan Hendrycks
- Trevor Darrell
- Dacheng Tao
- Ming-Hsuan Yang
- Alan L. Yuille
In Media Technology
- Evgenia Rusak
- Oliver Bringmann
- Thomas G. Dietterich
- Radha Poovendran
- Hossein Hosseini
- Roland S. Zimmermann
- Matthias Bethge
- Baicen Xiao
In Safety, Robustness & Interpretability
- Dan Hendrycks
- Thomas G. Dietterich
- Wieland Brendel
- Matthias Bethge
- Lukas Schott
- Matthias Hein
- Oliver Bringmann
- Evgenia Rusak
Citations in the corpus
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (2019, background): “Dodge & Karam (2017a) address underfitting via a mixture of corruption-specific experts assuming corruptions are known beforehand.”
- Increasing the robustness of DNNs against image corruptions by playing the Game of Noise (2020, methodology): “Two recent studies compare humans and DNNs on recognizing corrupted images, showing that DNN performance drops much faster than human performance for increased perturbation sizes [Dodge and Karam, 2017a, Geirhos et al., 2018].”
- Google's Cloud Vision API is Not Robust to Noise (2017, background): “It has been also observed that augmenting training data with perturbed images can enhance the model robustness [13], [18].”