Description: MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include “train MAL”, “Mask Auto-Label”, “weakly-supervised segmentation”, “box-prompted segmentation”, “minimal-annotation mask prediction”.
Lines: 222 | Code: 43 | Dir: tao-train-mask-auto-label
name: tao-train-mask-auto-label description: MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT…