Results for "pixel classes"

Pixel-wise classification of image regions.

When some classes are rare, requiring reweighting, resampling, or specialized metrics.

Pixel-level separation of individual object instances.

A measurable property or attribute used as model input (raw or engineered), such as age, pixel intensity, or token ID.

A table summarizing classification outcomes, foundational for metrics like precision, recall, specificity.

Pixel motion estimation between frames.

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.

Scalar summary of ROC; measures ranking ability, not calibration.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Plots true positive rate vs false positive rate across thresholds; summarizes separability.

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.

Diffusion performed in latent space for efficiency.

Assigning category labels to images.

Ensuring models comply with lending fairness laws.

Maximum expected loss under normal conditions.