HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Video Instance Segmentation On Youtube Vis 2

评估指标

AP50
AP75
AR1
AR10
mask AP

评测结果

各个模型在此基准测试上的表现结果

Paper Title
CAVIS(VIT-L, Offline)87.373.249.770.365.3Context-Aware Video Instance Segmentation
DVIS++(VIT-L, Offline)86.771.548.869.563.9DVIS++: Improved Decoupled Framework for Universal Video Segmentation
DVIS-DAQ(VIT-L, Offline)86.172.249.670.764.5DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
RefineVIS (Swin-L, online)84.168.548.365.261.4RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
DVIS(Swin-L)83.068.447.765.760.1DVIS: Decoupled Video Instance Segmentation Framework
DVIS++(VIT-L, Online)82.770.249.568.062.3DVIS++: Improved Decoupled Framework for Universal Video Segmentation
NOVIS (Swin-L)82.066.547.964.459.8NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
TarViS (Swin-L)81.467.647.664.860.2TarViS: A Unified Approach for Target-based Video Segmentation
GRAtt-VIS (Swin-L)81.367.148.864.560.3GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation
GenVIS (Swin-L)80.966.549.164.760.1A Generalized Framework for Video Instance Segmentation
IDOL (Swin-L)80.863.54560.156.1In Defense of Online Models for Video Instance Segmentation
MDQE(Swin-L)80.761.745.460.655.5MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos
VITA (Swin-L)80.661.047.762.657.5VITA: Video Instance Segmentation via Object Token Association
UniVS(Swin-L)79.463.346.263.157.9UniVS: Unified and Universal Video Segmentation with Prompts as Queries
Tube-Link(Swin-L)79.464.347.563.658.4Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
DeVIS (Swin-L)77.759.843.857.854.4DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
MinVIS (Swin-L)76.66245.960.855.3MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
BoxVIS(Swin-L & Box-sup)76.459.644.861.053.9BoxVIS: Video Instance Segmentation with Box Annotations
InstanceFormer (Swin-L)73.756.942.856.051.0InstanceFormer: An Online Video Instance Segmentation Framework
TarViS (Swin-T)71.656.642.257.250.9TarViS: A Unified Approach for Target-based Video Segmentation
0 of 26 row(s) selected.