's in this subset is even or odd.

We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process.

Segmentation, the task of delineating and isolating distinct objects, is a fundamental problem in computer vision. Much of the current approaches are supervised, relying on expensive manual annotations.

The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on different subgroups.

While successful, these methods are mainly designed for sampling from unconstrained domains.