# Between-class Learning for Image Classification

arXiv: https://arxiv.org/abs/1711.10284 · HTML: https://mlsanity.com/paper/1711.10284/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2017.

## Built on by (most cited first, 30 of 50)

- [Does Knowledge Distillation Really Work?](https://mlsanity.com/paper/2106.05945/) (2021)
- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Open Domain Generalization with Domain-Augmented Meta-Learning](https://mlsanity.com/paper/2104.03620/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [TeachAugment: Data Augmentation Optimization Using Teacher Knowledge](https://mlsanity.com/paper/2202.12513/) (2022)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [Defending Against Image Corruptions Through Adversarial Augmentations](https://mlsanity.com/paper/2104.01086/) (2021)
- [A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective](https://mlsanity.com/paper/2208.09913/) (2022)
- [Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning](https://mlsanity.com/paper/2202.11915/) (2022)
- [On the Strong Correlation Between Model Invariance and Generalization](https://mlsanity.com/paper/2207.07065/) (2022)
- [PopulAtion Parameter Averaging (PAPA)](https://mlsanity.com/paper/2304.03094/) (2023)
- [MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection](https://mlsanity.com/paper/2111.10958/) (2021)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [Gradient-Based Adversarial and Out-of-Distribution Detection](https://mlsanity.com/paper/2206.08255/) (2022)
- [When to Learn What: Model-Adaptive Data Augmentation Curriculum](https://mlsanity.com/paper/2309.04747/) (2023)
- [Open-Set Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2405.19899/) (2024)
- [OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup](https://mlsanity.com/paper/2301.00965/) (2023)
- [USB: Universal-Scale Object Detection Benchmark](https://mlsanity.com/paper/2103.14027/) (2021)
- [Probing the Purview of Neural Networks via Gradient Analysis](https://mlsanity.com/paper/2304.02834/) (2023)
- [Human-in-the-Loop Mixup](https://mlsanity.com/paper/2211.01202/) (2022)
- [SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness](https://mlsanity.com/paper/2108.09929/) (2021)
- [Few-shot Adaptive Object Detection with Cross-Domain CutMix](https://mlsanity.com/paper/2208.14586/) (2022)
- [Learning Invariance from Generated Variance for Unsupervised Person Re-identification](https://mlsanity.com/paper/2301.00725/) (2023)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)

## Abstract (arXiv)

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 constraints 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% and 2.26% top-1 errors on ImageNet-1K and CIFAR-10, respectively.