Data-driven Approach, K-Nearest Neighbor, train/validation/test splits

L1,L2 distances, hyperparameter search, cross-validation

Image Classification

• The task of assigning an input image one label from a fixed set of categories
• One of the core problems in Computer Vision

Example

• A single image and assigns probabilities to 4 labels, {cat, dog, hat, mug}
• The cat image is 248 pixels wide, 400 pixels tall, and has three color(RGB) channels

image consists of 248 x 400 x 3 numbers, or a total of 297,600 numbers

• Each number is an integer that ranges from 0 (black) to 255 (white).
• Our task is to turn this quarter of a million numbers into a single label, such as “cat”.

Challenges

• Viewpoint variation

  A single instance of an object can be oriented in many ways with respect to the camera.

• Scale variation

  Visual classes often exhibit variation in their size.

• Deformation

  Many objects of interest are not rigid bodies and can be deformed in extreme ways.

• Occlusion

  The objects can be occluded. Sometimes a small portion of an object could be visible.