AugNet: Dynamic Test-Time Augmentation via Differentiable Functions

12/09/2022
by   Shohei Enomoto, et al.
0

Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness is essential for practical applications. To improve robustness, we study an image enhancement method that generates recognition-friendly images without retraining the recognition model. We propose a novel image enhancement method, AugNet, which is based on differentiable data augmentation techniques and generates a blended image from many augmented images to improve the recognition accuracy under distribution shifts. In addition to standard data augmentations, AugNet can also incorporate deep neural network-based image transformation, which further improves the robustness. Because AugNet is composed of differentiable functions, AugNet can be directly trained with the classification loss of the recognition model. AugNet is evaluated on widely used image recognition datasets using various classification models, including Vision Transformer and MLP-Mixer. AugNet improves the robustness with almost no reduction in classification accuracy for clean images, which is a better result than the existing methods. Furthermore, we show that interpretation of distribution shifts using AugNet and retraining based on that interpretation can greatly improve robustness.

READ FULL TEXT
research
07/05/2022

Generalization to translation shifts: a study in architectures and augmentations

We provide a detailed evaluation of various image classification archite...
research
07/17/2020

URIE: Universal Image Enhancement for Visual Recognition in the Wild

Despite the great advances in visual recognition, it has been witnessed ...
research
01/25/2019

Equivariant Transformer Networks

How can prior knowledge on the transformation invariances of a domain be...
research
06/16/2022

Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening

We investigate the problems and challenges of evaluating the robustness ...
research
12/05/2019

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Modern deep neural networks can achieve high accuracy when the training ...
research
10/15/2021

Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation

We investigate the robustness of vision transformers (ViTs) through the ...
research
02/24/2022

Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration

Diverse data augmentation strategies are a natural approach to improving...

Please sign up or login with your details

Forgot password? Click here to reset