Image Segmentation

Masked-attention Mask Transformer for Universal Image Segmentation

Highly Accurate Dichotomous Image Segmentation （ECCV 2022）

Image Segmentation with DeepLabv3

The Segment Anything Model (SAM) is a powerful and versatile image segmentation model. It leverages a "foundation model" approach, meaning it can be used for various segmentation tasks without needing to be specifically trained for each one.

Bilateral Reference for High-Resolution Dichotomous Image Segmentation (CAAI AIR 2024)

OneFormer: One Transformer to Rule Universal Image Segmentation

DeepLabV3+ model for high-accuracy binary image segmentation, trained to detect roofs (foreground vs background) and output a grayscale mask.