Geometric Data Augmentation Based on Feature Map Ensemble

07/22/2021
by   Takashi Shibata, et al.
0

Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by geometric transformation, such as large rotations. In this paper, we propose a novel CNN architecture that can improve the robustness against geometric transformations without modifying the existing backbones of their CNNs. The key is to enclose the existing backbone with a geometric transformation (and the corresponding reverse transformation) and a feature map ensemble. The proposed method can inherit the strengths of existing CNNs that have been presented so far. Furthermore, the proposed method can be employed in combination with state-of-the-art data augmentation algorithms to improve their performance. We demonstrate the effectiveness of the proposed method using standard datasets such as CIFAR, CUB-200, and Mnist-rot-12k.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2022

Local Magnification for Data and Feature Augmentation

In recent years, many data augmentation techniques have been proposed to...
research
08/07/2018

Data augmentation using synthetic data for time series classification with deep residual networks

Data augmentation in deep neural networks is the process of generating a...
research
12/02/2020

A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Deep neural networks are often not robust to semantically-irrelevant cha...
research
11/26/2017

JPEG Steganalysis Based on DenseNet

Current research has indicated that convolution neural networks (CNNs) c...
research
05/05/2022

Data Augmentation for Manipulation

The success of deep learning depends heavily on the availability of larg...
research
11/26/2021

Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors

Semantic scene completion (SSC) is a challenging Computer Vision task wi...
research
11/23/2015

What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks

Top-down information plays a central role in human perception, but plays...

Please sign up or login with your details

Forgot password? Click here to reset