HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Semantic Segmentation On Synpass

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

模型名称	mIoU	Paper Title	Repository
PVT	32.68%	Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Trans4PASS+	39.16%	Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
Fast-SCNN	21.30%	Fast-SCNN: Fast Semantic Segmentation Network
DeepLabv3+	29.66%	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Trans4PASS	38.57%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
SegFomrer	37.24%	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

0 of 6 row(s) selected.