Add to ORKGIn this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-art performance on a wide range of computer vision tasks. We present a general stability training method to stabilize deep networks against small input distortions that result from various types of common image processing, such as compression, rescaling, and cropping. We validate our method by stabilizing the state of-the-art Inception architecture [11] against these types of distortions. In addition, we demonstrate that our stabilized model gives robust state-of-the-art perf...
Deep learning has had a tremendous impact in the field of computer vision. However, the deployment o...
Deep neural networks have become a ubiquitous tool in a broad range of AI applications. Resembling i...
Over the past decade, compressive sensing and deep learning have emerged as viable techniques for re...
In this paper we address the issue of output instability of deep neural networks: small perturbation...
We introduce several new datasets namely ImageNet-A/O and ImageNet-R as well as a synthetic environm...
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object ...
Convolutional neural networks (CNNs) lack robustness to test image corruptions that are not seen dur...
Deep neural networks have achieved impressive results in many image classification tasks. However, s...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
In recent years, deep architectures have been used for transfer learning with state-of-the-art perfo...
Convolutional neural networks (CNNs) lack robustness to test image corruptions that are not seen dur...
Deep neural networks have achieved state-of-the-art performance in many artificial intelligence area...
Deep learning, due to its unprecedented success in tasks such as image classification, has emerged a...
Deep learning has had a tremendous impact in the field of computer vision. However, the deployment o...
Deep neural networks have become a ubiquitous tool in a broad range of AI applications. Resembling i...
Over the past decade, compressive sensing and deep learning have emerged as viable techniques for re...
In this paper we address the issue of output instability of deep neural networks: small perturbation...
We introduce several new datasets namely ImageNet-A/O and ImageNet-R as well as a synthetic environm...
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object ...
Convolutional neural networks (CNNs) lack robustness to test image corruptions that are not seen dur...
Deep neural networks have achieved impressive results in many image classification tasks. However, s...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their suc...
In recent years, deep architectures have been used for transfer learning with state-of-the-art perfo...
Convolutional neural networks (CNNs) lack robustness to test image corruptions that are not seen dur...
Deep neural networks have achieved state-of-the-art performance in many artificial intelligence area...
Deep learning, due to its unprecedented success in tasks such as image classification, has emerged a...
Deep learning has had a tremendous impact in the field of computer vision. However, the deployment o...
Deep neural networks have become a ubiquitous tool in a broad range of AI applications. Resembling i...
Over the past decade, compressive sensing and deep learning have emerged as viable techniques for re...