Pith. sign in

REVIEW 24 cited by

Image Data Augmentation for Deep Learning: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.08610 v2 pith:VJP2PHGX submitted 2022-04-19 cs.CV

Suorong Yang , Weikang Xiao , Mengchen Zhang , Suhan Guo , Jian Zhao , Furao Shen This is my paper · ORCID
classification cs.CV
keywords dataaugmentationdeepimagelearningmethodstrainingbecome
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 24 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving Backward Conformal Prediction via Non-Conformity Score Transformation

    stat.ML 2026-02 reject novelty 7.0 of 10

    ST-BCP tightens the coverage bound in Backward Conformal Prediction by applying a computable data-dependent transformation to nonconformity scores, reducing the average gap from 4.20% to 1.12% on benchmarks while prov...

  2. Beyond and Free from Diffusion: Invertible Guided Consistency Training

    cs.CV 2025-02 conditional novelty 7.0 of 10

    iGCT trains guided consistency models from scratch by mixing the original noise with a direction to a random target-class image, and reports better FID and precision than classifier-free guidance at high guidance on CIFAR-10.

  3. Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Aggressive color data augmentation makes VLA robot models lighting-robust by teaching them to ignore color, causing failure on benign color-dependent tasks; fixing hue during adversarial training (ChromaGuard) preserves both.

  4. Learning from Noise: Enhancing DNNs for Event-Based Vision through Controlled Noise Injection

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Adding synthetic shot noise at random intensities to event-camera training data makes CNN, ViT, SNN, and GCN classifiers robust to input noise, outperforming test-time filtering.

  5. Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation

    astro-ph.IM 2025-01 conditional novelty 6.0 of 10

    A multi-survey CNN estimates photometric redshifts from GALEX, PanSTARRS, and UnWISE cutouts, with early and late image fusion performing comparably.

  6. Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A group-classification plus multi-expert regression framework with symmetric descending soft labels improves deep imbalanced regression on age and text-similarity benchmarks.

  7. PopSweeper: Automatically Detecting and Resolving App-Blocking Pop-Ups to Assist Automated Mobile GUI Testing

    cs.SE 2024-12 conditional novelty 6.0 of 10

    PopSweeper detects app-blocking pop-ups in mobile GUI screenshots with 93.5% recall and localizes their close buttons, but its real-time resolution claim is validated only in simulation.

  8. Image Quality Dependent Degradation for AI Systems

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A normalizing-flow quality monitor that lowers an object detector's confidence threshold on low-quality images raises pedestrian recall by a few points while slightly reducing precision.

  9. Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

    cs.CR 2026-07 conditional novelty 5.0 of 10

    GAN-based augmentation of poisoned 3D point cloud datasets amplifies attack effectiveness, increasing misclassification and operational impact on CAV decision-making by up to 3x compared to non-augmented baselines.

  10. NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Mixing the estimated noise of two class prompts at each denoising step of Stable Diffusion generates natural augmented images that improve fine-grained classification over CutMix on some datasets.

  11. Group Relative Augmentation for Data Efficient Action Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A LoRA plus FiLM feature-augmentation method with a group-weighted loss reports modest few-shot action detection gains on AVA and MOMA, but the evidence for the weighting component is weak.

  12. Curvature Enhanced Data Augmentation for Regression

    cs.LG 2025-06 conditional novelty 5.0 of 10

    CEMS augments regression training by sampling from a second-order, curvature-aware local model of the joint input-output manifold, and reports competitive in-distribution and out-of-distribution results on nine benchmarks.

  13. Automatic detection of overshooting tops and their properties from visible satellite channels

    physics.ao-ph 2025-05 conditional novelty 5.0 of 10

    A CNN trained on about 10,000 manually labeled European cases detects overshooting tops from visible satellite images with 97.7% probability of detection and estimates their height with a mean error of about 0.25 km.

  14. An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A Grad-CAM-based methodology with similarity metrics reveals that data augmentation techniques affect learned attention patterns in distinct clusters, but individual differences are small.

  15. When Dynamic Data Selection Meets Data Augmentation

    cs.LG 2025-05 reject novelty 5.0 of 10

    A training framework that selects low-density, semantically consistent samples for light augmentation, claiming 50% cost reduction on ImageNet-1k with lossless performance.

  16. SGIA: Enhancing Fine-Grained Visual Classification with Sequence Generative Image Augmentation

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A sequence generated from a single image with a latent diffusion model improves fine-grained classification accuracy slightly over strong baselines.

  17. Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data

    cs.LG 2024-12 reject novelty 5.0 of 10

    A UCB-based training procedure switches between a diversity/photorealism score and a feature-cohesion score to select synthetic training images, reporting up to 10-point accuracy gains over static metrics.

  18. AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Fine-tuned Protogen v3.4 generates novel Ulos motifs with ~10.5 imes lower FID and 2× higher IS than Stable Diffusion v1.4, with guidance scale 5–9 balancing fidelity and diversity.

  19. Hybrid Ensemble Approaches: Optimal Deep Feature Fusion and Hyperparameter-Tuned Classifier Ensembling for Enhanced Brain Tumor Classification

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A double ensemble that fuses features from pretrained CNNs and ViTs and ensembles tuned ML classifiers reaches 97.5% to 99.3% accuracy on three public brain MRI datasets, but the gains are not benchmarked against a he...

  20. Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classification

    cs.CV 2025-06 reject novelty 4.0 of 10

    A ViT feature ensemble plus ML classifier voting pipeline is evaluated on two binary brain MRI datasets, reporting up to 99.8% accuracy without a same-dataset comparison against prior methods.

  21. Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis

    cs.CV 2025-09 reject novelty 3.0 of 10

    Attention-augmented CNNs usually beat plain CNNs on two medical image datasets, with EfficientNetB5 plus hybrid attention the best, but test-set-based model selection undermines the claimed consistency.

  22. 3D Skeleton-Based Action Recognition: A Review

    cs.CV 2025-06 reject novelty 3.0 of 10

    A task-oriented review of skeleton-based action recognition that reorganizes known methods along a data processing pipeline and contains no new experimental result.

  23. Crowd Scene Analysis using Deep Learning Techniques

    cs.CV 2025-05 reject novelty 3.0 of 10

    The paper describes a 5-column M-CNN with rotation self-supervision and Sinkhorn distribution matching for crowd counting and a VGG19-LSTM with dense residual blocks for violence detection, but the evidence does not s...

  24. Remote Sensing Imagery for Flood Detection: Exploration of Augmentation Strategies

    cs.CV 2025-04 conditional novelty 3.0 of 10

    Distortion and blur/noise augmentations give the best floodwater segmentation results on BlessemFlood21; color augmentations give the worst, with small overall differences.

Pith tools