DeepAI AI Chat
Log In Sign Up

Between-class Learning for Image Classification

by   Yuji Tokozume, et al.
The University of Tokyo

In this paper, we propose a novel learning method for image classification called Between-Class learning (BC learning). We generate between-class images by mixing two images belonging to different classes with a random ratio. We then input the mixed image to the model and train the model to output the mixing ratio. BC learning has the ability to impose a constraint on the shape of the feature distributions, and thus the generalization ability is improved. BC learning is originally a method developed for sounds, which can be digitally mixed. Mixing two image data does not appear to make sense; however, we argue that because convolutional neural networks have an aspect of treating input data as waveforms, what works on sounds must also work on images. First, we propose a simple mixing method using internal divisions, which surprisingly proves to significantly improve performance. Second, we propose a mixing method that treats the images as waveforms, which leads to a further improvement in performance. As a result, we achieved 19.4 ImageNet-1K and CIFAR-10, respectively.


Learning from Between-class Examples for Deep Sound Recognition

Deep learning methods have achieved high performance in sound recognitio...

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

Recent strategies achieved ensembling "for free" by fitting concurrently...

Observations on K-image Expansion of Image-Mixing Augmentation for Classification

Image-mixing augmentations (e.g., Mixup or CutMix), which typically mix ...

SuperMix: Supervising the Mixing Data Augmentation

In this paper, we propose a supervised mixing augmentation method, terme...

SMMix: Self-Motivated Image Mixing for Vision Transformers

CutMix is a vital augmentation strategy that determines the performance ...

CRL: Class Representative Learning for Image Classification

Building robust and real-time classifiers with diverse datasets are one ...

Unified smoke and fire detection in an evolutionary framework with self-supervised progressive data augment

Few researches have studied simultaneous detection of smoke and flame ac...

Code Repositories


Chainer implementation of between-class learning for Image classification

view repo