Skip to main content

Menu

LEVEL 0
0/5 XP
HomeAboutTopicsPricingMy VaultStatsPractice TestsCertifications

Categories

🎓 Certifications
🤖 Artificial Intelligence
☁️ Cloud and Infrastructure
💾 Data and Databases
💼 Professional Skills
🎯 Programming and Development
🔒 Security and Networking
📚 Specialized Topics
CheatGrid
HomeAboutTopicsPricingMy VaultStatsPractice TestsCertifications
LVLEVEL 0
0/5 XP
GitHub
© 2026 CheatGrid™. All rights reserved.
Privacy PolicyTerms of UseAboutContact

Data Augmentation Strategies for Deep Learning Cheat Sheet

Data Augmentation Strategies for Deep Learning Cheat Sheet

Back to AI and Machine Learning
Updated 2026-05-02
Next Topic: Deep Learning Cheat Sheet

Data augmentation is a powerful regularization technique that artificially expands training datasets by creating modified copies of existing data, helping deep learning models generalize better to unseen examples. Augmentation techniques transform input data during training without requiring additional labeling effort, effectively addressing data scarcity and overfitting. Understanding when to apply simple geometric transformations versus advanced policy-based methods, and how to balance augmentation strength with model capacity, is critical — too weak augmentation leaves overfitting unaddressed, while overly aggressive augmentation can degrade training signal and slow convergence.

What This Cheat Sheet Covers

This topic spans 15 focused tables and 79 indexed concepts. Below is a complete table-by-table outline of this topic, spanning foundational concepts through advanced details.

Table 1: Basic Geometric TransformationsTable 2: Color and Photometric AugmentationsTable 3: Noise Injection TechniquesTable 4: Occlusion and Masking-Based RegularizationTable 5: Sample Mixing and Interpolation MethodsTable 6: Policy-Based and Automated AugmentationTable 7: Domain-Specific Augmentation TechniquesTable 8: Text and NLP-Specific AugmentationTable 9: GAN and Generative Model-Based AugmentationTable 10: Test-Time Augmentation and EnsemblingTable 11: Augmentation Pipeline Design and ImplementationTable 12: Self-Supervised and Contrastive Learning AugmentationTable 13: Augmentation Scheduling and Curriculum LearningTable 14: Adversarial and Robustness-Oriented AugmentationTable 15: Knowledge Distillation and Augmentation

Table 1: Basic Geometric Transformations

The workhorses of image augmentation — flips, rotations, crops, and affine or perspective warps that move pixels around in space while leaving the label intact. They're cheap, intuitive, and almost always your first line of defence against overfitting, though each carries a caveat about when it stops being label-preserving (a flipped digit or rotated road sign can change meaning).

TechniqueExampleDescription
Horizontal and Vertical Flipping
transforms.RandomHorizontalFlip(p=0.5)
• Mirrors image along horizontal or vertical axis with probability p
• Preserves semantic content while introducing rotational invariance
• Valid only when orientation doesn't affect label (not suitable for text or directional signs)
Random Rotation
A.Rotate(limit=15, p=0.8)
• Rotates image by random angle within [-limit, +limit] degrees
• Small angles (±15°) preserve context while introducing orientation invariance
• Large rotations may create unrealistic perspectives or crop important regions
Random Cropping
transforms.RandomCrop(size=224)
• Extracts random spatial region of specified size from image
• Forces model to learn from partial views and distributed features rather than relying on single discriminative patches
• Commonly combined with resizing to target input dimensions
Random Resized Crop
transforms.RandomResizedCrop(224,
scale=(0.8, 1.0))
• Crops random patch at scale \in [0.8, 1.0] of original area, then resizes to target size
• Simulates objects at different distances from camera
• More effective than simple cropping as it combines scale and translation invariance
Affine Transformations
A.Affine(translate_percent=0.1,
scale=(0.9, 1.1), shear=10)
• Applies translation, scaling, rotation, and shear simultaneously while preserving parallel lines
• Defined by 6 parameters in 2 \times 3 matrix
• Simulates viewpoint changes without perspective distortion

More in AI and Machine Learning

  • Convolutional Neural Networks (CNNs) Cheat Sheet
  • Deep Learning Cheat Sheet
  • AI Bias & Fairness Cheat Sheet
  • Feature Engineering Cheat Sheet
  • MLflow Cheat Sheet
  • PyTorch Cheat Sheet
View all 83 topics in AI and Machine Learning