Semantic Segmentation

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

Transformer applied to image patches.

Joint vision-language model aligning images and text.

Combining signals from multiple modalities.

Attention between different modalities.

Identifying and localizing objects in images, often with confidence scores and bounding rectangles.

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

Assigning category labels to images.

Pixel-level separation of individual object instances.