Segmentation · Google Research
DeepLab: Atrous Convolution for Semantic Segmentation
DeepLab turns semantic image segmentation into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Topics
Segmentation
Promptable and automatic systems for separating objects in images and videos.
Mask R-CNN: Instance Segmentation on Top of Faster R-CNN
Mask R-CNN turns instance segmentation into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Segmentation · Independent Researcher
U-Net: The Biomedical Image Segmentation Baseline
U-Net turns biomedical image segmentation into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Mask2Former: One Transformer for Segmentation Tasks
Mask2Former uses masked attention to unify semantic, instance, and panoptic segmentation, reaching 57.8 PQ on COCO panoptic and 57.7 mIoU on ADE20K.
Segment Anything (SAM): One Promptable Model, a Billion Masks
Meta AI's SAM treats segmentation as a promptable task and ships with SA-1B (1.1B masks on 11M images), letting one model transfer zero-shot to new objects and image distributions.
SAM 2 Explained: Promptable Segmentation Across Video
SAM 2 carries one click through a whole video using a streaming memory module, hitting better masks with 3x fewer interactions than prior video methods and running 6x faster than SAM on images.