Semantic Segmentation on Lyft Level 5

Metric: IoU vehicle - 224x480 - Short (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	IoU vehicle - 224x480 - Short▼	Extra Data	Paper	Date↕	Code
1	PointBeV (EfficientNet-b4)	72.6	No	PointBeV: A Sparse Approach to BeV Predictions	2023-12-01	Code
2	PointBeV (ResNet-50)	72.3	No	PointBeV: A Sparse Approach to BeV Predictions	2023-12-01	Code
3	Simple-BEV (ResNet-50)	70.7	No	Simple-BEV: What Really Matters for Multi-Sensor...	2022-06-16	Code
4	Simple-BEV (EfficientNet-b4)	70.4	No	Simple-BEV: What Really Matters for Multi-Sensor...	2022-06-16	Code
5	BEVFormer (EfficientNet-b4)	69.9	No	BEVFormer: Learning Bird's-Eye-View Representati...	2022-03-31	Code
6	BEVFormer(ResNet-50)	68.8	No	BEVFormer: Learning Bird's-Eye-View Representati...	2022-03-31	Code
7	FIERY	59.4	No	FIERY: Future Instance Prediction in Bird's-Eye ...	2021-04-21	Code

#1PointBeV (EfficientNet-b4)SOTA
72.6
IoU vehicle - 224x480 - Short· 2023-12-01
PointBeV: A Sparse Approach to BeV Predictions Code
#2PointBeV (ResNet-50)
72.3
IoU vehicle - 224x480 - Short· 2023-12-01
PointBeV: A Sparse Approach to BeV Predictions Code
#3Simple-BEV (ResNet-50)SOTA
70.7
IoU vehicle - 224x480 - Short· 2022-06-16
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?Code
#4Simple-BEV (EfficientNet-b4)
70.4
IoU vehicle - 224x480 - Short· 2022-06-16
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?Code
#5BEVFormer (EfficientNet-b4)SOTA
69.9
IoU vehicle - 224x480 - Short· 2022-03-31
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers Code
#6BEVFormer(ResNet-50)
68.8
IoU vehicle - 224x480 - Short· 2022-03-31
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers Code
#7FIERYSOTA
59.4
IoU vehicle - 224x480 - Short· 2021-04-21
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras Code