Instance Segmentation On Cityscapes

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

	Paper Title
Learnable Margin	Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth
Dynamically Instantiated Network	Pixelwise Instance Segmentation with a Dynamically Instantiated Network
Panoptic-DeepLab [Cityscapes-fine]	Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
モデル 4	Track to Detect and Segment: An Online Multi-Object Tracker
Semantic Instance Segmentation with a Discriminative Loss Function	Semantic Instance Segmentation with a Discriminative Loss Function
EfficientPS	EfficientPS: Efficient Panoptic Segmentation
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth	Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth
Panoptic-DeepLab [Mapillary Vistas]	Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
Deep Watershed Transform	Deep Watershed Transform for Instance Segmentation
GAIS-Net	Geometry-Aware Instance Segmentation with Disparity Maps
PolyTransform	PolyTransform: Deep Polygon Transformer for Instance Segmentation

0 of 11 row(s) selected.