By adding distortions to the R, G, and B values of images, we still get images in which the same objects are recognizable.

Color Shifting for Data Augmentation in Image Recognition Through Deep Learning

Image augmentation leverages random operations to generate diverse, novel images from existing training data. Due to this stochastic nature, applying the exact same augmentation procedure multiple times to a single image will yield distinct, randomized variations. This deliberate introduction of randomness dynamically expands the dataset and is fundamentally designed to improve the generalization ability of deep learning models.

Randomness in Image Augmentation

Flipping an image horizontally (left-to-right) or vertically (up-and-down) is a foundational and widely used image augmentation technique. Because flipping typically does not alter the category of the object depicted, it safely expands the dataset. While horizontal flipping is extremely common, vertical flipping is employed less frequently but remains useful when the vertical orientation of objects does not hinder recognition.

Image Flipping Augmentation

In deep learning practice, a single augmentation technique is rarely applied in isolation. Instead, multiple distinct image augmentation methods—such as horizontal flipping, random resized cropping, and color jittering—are combined into a unified transformation pipeline. By applying these diverse transformations sequentially through a composition function (often denoted as `Compose`), the range of possible random variations per image increases significantly, yielding more robust and invariant models.

Combining Image Augmentation Methods

For example, instead of taking more cat pictures, you can use one or a combination of the following methods:
- Mirroring (Horizontally/vertically flipping)
- Random cropping (Zooming in)
- Rotating
- Shearing
- Local wrapping
- Color shifting

University of Michigan - Ann Arbor

Getting more data may be costly and an ineffective way to prevent overfitting. However, you can augment your data to create more. We are adding synthetic data modified from our original data set. You essentially transform your data in a way where it is different form the original, but the data still fits into your given class. It is much more efficient and cost effective. 

Data Augmentation in Deep Learning

Methods of Data Augmentation in Image Recognition Through Deep Learning

- To improve the robustness of the neural network in speech recognition, noise injection is a method we can apply by adding random noise in the input to the neural network. One of the examples is to inject Gaussian noise into the input. 
- Applying noise injection to the hidden units can be highly effective when we tune the magnitude of the noise carefully. 

Data Augmentation in Speech Recognition Through Deep Learning

When applying deep learning models to tasks on a different dataset, the image augmentation operations must often be modified to account for differing image characteristics. For instance, images within the ImageNet dataset are typically larger and possess varying dimensions, in stark contrast to the images found in the CIFAR-10 dataset. Consequently, an augmentation pipeline designed for one dataset must be explicitly adjusted to suit the resolution and geometric properties of the new target dataset.

Learn Before

Related

Learn After