Home Knowledge Base TrivialAugment

TrivialAugment is the simplest possible automated augmentation strategy that matches or exceeds complex learned policies — applying exactly one randomly selected transformation at a randomly selected magnitude to each training image, with zero hyperparameters to tune, proving the counterintuitive result that the "dumbest" approach to augmentation is as effective as sophisticated search-based methods like AutoAugment.

What Is TrivialAugment?

Algorithm (Complete)

For each training image:
    1. Randomly select ONE operation from the pool
    2. Randomly select a magnitude (uniform from 0 to max)
    3. Apply the operation at that magnitude
    Done.

That's the entire algorithm. No loops, no parameters, no search.

Comparison of Augmentation Complexity

MethodHyperparametersSearch CostAlgorithm Complexity
No Augmentation00None
Manual AugmentationMany (per-transform)Human timeHand-tuned
AutoAugment25 sub-policies × 2 ops × 3 params5,000 GPU hoursRL controller + proxy training
RandAugment2 (N and M)Grid searchRandom selection, fixed magnitude
TrivialAugment00Single random operation

Why Zero Hyperparameters Wins

InsightExplanation
Random magnitude = implicit adaptiveEach image gets a different strength — some mild, some strong, naturally covering the space
One operation = maximum diversityOver a training epoch, every operation appears equally — no bias toward specific transforms
No overfitting to augmentationLearned policies can overfit to the proxy task or validation set
No computational wasteZero search cost means all compute goes to actual training

Results: Trivial = SOTA

DatasetModelAutoAugmentRandAugmentTrivialAugment
CIFAR-10WRN-40-23.70%3.60%3.40%
CIFAR-100WRN-40-218.40%18.60%18.10%
ImageNetResNet-5022.40%22.40%22.10%

TrivialAugment matches or beats all more complex methods — with zero hyperparameters and zero search cost.

The Broader Lesson

TrivialAugment demonstrates a recurring theme in machine learning: simple methods with good inductive biases often match complex methods. The specific augmentation policy matters less than having diverse augmentations applied consistently during training.

TrivialAugment is the proof that simplicity wins in data augmentation — achieving state-of-the-art results with zero hyperparameters and zero search cost by randomly applying a single transformation at a random strength to each training image, challenging the assumption that complex learned augmentation policies are necessary for strong performance.

trivialaugmentsinglerandom

Explore 500+ Semiconductor & AI Topics

From EUV lithography to CUDA optimization — search the full knowledge base or chat with our AI assistant.