# DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

arXiv: https://arxiv.org/abs/1809.00981 · HTML: https://mlsanity.com/paper/1809.00981/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2018.

## Built on by (most cited first, 18 of 18)

- [Chaos as an interpretable benchmark for forecasting and data-driven modelling](https://mlsanity.com/paper/2110.05266/) (2021)
- [Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations](https://mlsanity.com/paper/2207.01164/) (2022)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2202.06464/) (2022)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation](https://mlsanity.com/paper/2106.11892/) (2021)
- [Image Classification with Small Datasets: Overview and Benchmark](https://mlsanity.com/paper/2212.12478/) (2022)
- [Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study](https://mlsanity.com/paper/2107.12202/) (2021)
- [Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime](https://mlsanity.com/paper/2211.15961/) (2022)
- [ProtoKD: Learning from Extremely Scarce Data for Parasite Ova Recognition](https://mlsanity.com/paper/2309.10210/) (2023)
- [MVAD: A Multiple Visual Artifact Detector for Video Streaming](https://mlsanity.com/paper/2406.00212/) (2024)
- [HARD: Hard Augmentations for Robust Distillation](https://mlsanity.com/paper/2305.14890/) (2023)
- [No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets](https://mlsanity.com/paper/2309.01694/) (2023)
- [On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study](https://mlsanity.com/paper/2104.02653/) (2021)
- [DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta](https://mlsanity.com/paper/2207.10271/) (2022)
- [Confidence-Guided Data Augmentation for Improved Semi-Supervised Training](https://mlsanity.com/paper/2209.08174/) (2022)
- [Use the Detection Transformer as a Data Augmenter](https://mlsanity.com/paper/2304.04554/) (2023)

## Abstract (arXiv)

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. All results endorse the superior capability of DADA in enhancing the generalization ability of deep networks trained in practical extremely low data regimes. Source code is available at https://github.com/SchafferZhang/DADA.