Skip to content
Quantoros

How to choose which augmentations to use?

Computer VisionLevel: IntermediateNeural networks for computer vision

How to choose which augmentations to use?

Hints
  • Identify the prediction unit: image, object, pixel or sequence.
  • How do occlusion, lighting or domain changes affect results and evaluation?

Answer

Augmentations really depend on the type of output classes and the features you want your model to learn. For eg. if you have mostly properly illuminated images in your dataset and want your model to predict poorly illuminated images too, you can apply channel shifting on your data and include the resultant images in your dataset for better results.

Source and licence: Alexey Grigorev & contributors — Data Science Interviews · CC-BY-4.0

Related questions