DeepAI AI Chat
Log In Sign Up

Swapping Semantic Contents for Mixing Images

by   Rémy Sun, et al.

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised Learning. Mixing Data Augmentations do not typically yield new labeled samples, as indiscriminately mixing contents creates between-class samples. In this work, we introduce the SciMix framework that can learn to generator to embed a semantic style code into image backgrounds, we obtain new mixing scheme for data augmentation. We then demonstrate that SciMix yields novel mixed samples that inherit many characteristics from their non-semantic parents. Afterwards, we verify those samples can be used to improve the performance semi-supervised frameworks like Mean Teacher or Fixmatch, and even fully supervised learning on a small labeled dataset.


page 1

page 2


Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

We propose Dense FixMatch, a simple method for online semi-supervised le...

Analysis of Semi-Supervised Methods for Facial Expression Recognition

Training deep neural networks for image recognition often requires large...

Confidence-Guided Data Augmentation for Deep Semi-Supervised Training

We propose a new data augmentation technique for semi-supervised learnin...

Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic Mixtures

We study the problem of semi-supervised singing voice separation, in whi...

Adversarial Mixup Resynthesizers

In this paper, we explore new approaches to combining information encode...

Data Augmentation of IMU Signals and Evaluation via a Semi-Supervised Classification of Driving Behavior

Over the past years, interest in classifying drivers' behavior from data...

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation

Optical character recognition (OCR) systems performance have improved si...