Research Papers Topics
Promptable and automatic systems for separating objects in images and videos.
Segmentation · Mask2Former vs Mask R-CNN vs SAM vs SAM 2
Mask2Former beats Mask R-CNN 43.7 to 37.2 COCO AP at ResNet-50 in one table; SAM gets 46.5 zero-shot COCO AP vs 51.0 supervised ViTDet-H; SAM 2 hits 76.8 J&F on SA-V val vs XMem 60.1, 6x faster than SAM.
Segmentation · Google Research
DeepLab turns semantic image segmentation into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
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 turns biomedical image segmentation into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Mask2Former uses masked attention to unify semantic, instance, and panoptic segmentation, reaching 57.8 PQ on COCO panoptic and 57.7 mIoU on ADE20K.
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 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.