HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Interactive Segmentation On Berkeley

Metrics

NoC@90

Results

Performance results of various models on this benchmark

Model Name
NoC@90
Paper TitleRepository
SimpleClick (ViT-H, C+L)1.75SimpleClick: Interactive Image Segmentation with Simple Vision Transformers-
f-BRS-B (ResNet-50)4.34f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation-
UCP-Net2.70UCP-Net: Unstructured Contour Points for Instance Segmentation-
ViT-B+MST+CL1.50MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation-
CM guidance5.60Content-Aware Multi-Level Guidance for Interactive Instance Segmentation-
ICL CFR-1 (ViT-H, C+L)1.46CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation-
SimpleClick (ViT-H, SBD)2.09SimpleClick: Interactive Image Segmentation with Simple Vision Transformers-
RITM (HRNet18, SBD)3.22Reviving Iterative Training with Mask Guidance for Interactive Segmentation-
FocalClick-B3-S21.48FocalClick: Towards Practical Interactive Image Segmentation-
RITM (HRNet18, C+L)2.26Reviving Iterative Training with Mask Guidance for Interactive Segmentation-
BRS5.08Interactive Image Segmentation via Backpropagating Refinement Scheme-
EdgeFlow2.4EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow-
IA+SA4.94Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections-
IA-FP-Net(HRNet, C+L)2.12Cascaded Sparse Feature Propagation Network for Interactive Segmentation-
0 of 14 row(s) selected.
Interactive Segmentation On Berkeley | SOTA | HyperAI