DeepAI
Log In Sign Up

Evolving Image Compositions for Feature Representation Learning

06/16/2021
by   Paola Cascante-Bonilla, et al.
0

Convolutional neural networks for visual recognition require large amounts of training samples and usually benefit from data augmentation. This paper proposes PatchMix, a data augmentation method that creates new samples by composing patches from pairs of images in a grid-like pattern. These new samples' ground truth labels are set as proportional to the number of patches from each image. We then add a set of additional losses at the patch-level to regularize and to encourage good representations at both the patch and image levels. A ResNet-50 model trained on ImageNet using PatchMix exhibits superior transfer learning capabilities across a wide array of benchmarks. Although PatchMix can rely on random pairings and random grid-like patterns for mixing, we explore evolutionary search as a guiding strategy to discover optimal grid-like patterns and image pairing jointly. For this purpose, we conceive a fitness function that bypasses the need to re-train a model to evaluate each choice. In this way, PatchMix outperforms a base model on CIFAR-10 (+1.91), CIFAR-100 (+5.31), Tiny Imagenet (+3.52), and ImageNet (+1.16) by significant margins, also outperforming previous state-of-the-art pairwise augmentation strategies.

READ FULL TEXT

page 1

page 2

page 7

page 12

11/22/2018

Data Augmentation using Random Image Cropping and Patching for Deep CNNs

Deep convolutional neural networks (CNNs) have achieved remarkable resul...
05/13/2019

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Regional dropout strategies have been proposed to enhance the performanc...
06/02/2020

SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization

Advanced data augmentation strategies have widely been studied to improv...
02/23/2022

Image Classification on Small Datasets via Masked Feature Mixing

Deep convolutional neural networks require large amounts of labeled data...
12/18/2013

Unsupervised feature learning by augmenting single images

When deep learning is applied to visual object recognition, data augment...
02/03/2020

Radioactive data: tracing through training

We want to detect whether a particular image dataset has been used to tr...
03/09/2021

A Data Augmentation Method by Mixing Up Negative Candidate Answers for Solving Raven's Progressive Matrices

Raven's Progressive Matrices (RPMs) are frequently-used in testing human...