# APAC: Augmented PAttern Classification with Neural Networks

arXiv: https://arxiv.org/abs/1505.03229 · HTML: https://mlsanity.com/paper/1505.03229/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2015.

## Built on by (most cited first, 23 of 23)

- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Open Domain Generalization with Domain-Augmented Meta-Learning](https://mlsanity.com/paper/2104.03620/) (2021)
- [Vision-Language Navigation with Random Environmental Mixup](https://mlsanity.com/paper/2106.07876/) (2021)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [CLCC: Contrastive Learning for Color Constancy](https://mlsanity.com/paper/2106.04989/) (2021)
- [Automated Data Augmentations for Graph Classification](https://mlsanity.com/paper/2202.13248/) (2022)
- [Interpreting the Robustness of Neural NLP Models to Textual Perturbations](https://mlsanity.com/paper/2110.07159/) (2021)
- [A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks](https://mlsanity.com/paper/2206.06544/) (2022)
- [The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition](https://mlsanity.com/paper/2105.13061/) (2021)
- [PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds](https://mlsanity.com/paper/2210.13428/) (2022)
- [Contrastive Learning with Consistent Representations](https://mlsanity.com/paper/2302.01541/) (2023)
- [Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media](https://mlsanity.com/paper/2403.00037/) (2024)
- [Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification](https://mlsanity.com/paper/2101.02353/) (2021)
- [MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis](https://mlsanity.com/paper/2306.17466/) (2023)
- [Test-Time Augmentation for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2311.13152/) (2023)
- [Signature-Graph Networks](https://mlsanity.com/paper/2110.11551/) (2021)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)
- [Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillation](https://mlsanity.com/paper/2507.01347/) (2025)
- [InAugment: Improving Classifiers via Internal Augmentation](https://mlsanity.com/paper/2104.03843/) (2021)
- [Analyzing the effectiveness of image augmentations for face recognition from limited data](https://mlsanity.com/paper/2105.08796/) (2021)
- [Pruning Distorted Images in MNIST Handwritten Digits](https://mlsanity.com/paper/2307.14343/) (2023)
- [Designing Compact Neural Architectures via Neuron Gating and Mixed Activation](https://mlsanity.com/paper/2608.14443/) (2026)

## Abstract (arXiv)

Deep neural networks have been exhibiting splendid accuracies in many of visual pattern classification problems. Many of the state-of-the-art methods employ a technique known as data augmentation at the training stage. This paper addresses an issue of decision rule for classifiers trained with augmented data. Our method is named as APAC: the Augmented PAttern Classification, which is a way of classification using the optimal decision rule for augmented data learning. Discussion of methods of data augmentation is not our primary focus. We show clear evidences that APAC gives far better generalization performance than the traditional way of class prediction in several experiments. Our convolutional neural network model with APAC achieved a state-of-the-art accuracy on the MNIST dataset among non-ensemble classifiers. Even our multilayer perceptron model beats some of the convolutional models with recently invented stochastic regularization techniques on the CIFAR-10 dataset.