Semantic Segmentation On Dada Seg

Metriken

mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	mIoU	Paper Title
CLAN	28.76	Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
DNL (ResNet-101)	19.7	Disentangled Non-Local Neural Networks
ResNet-50	18.96	Deep Residual Learning for Image Recognition
ISSAFE	29.97	ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
SIM	26.85	Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
HRNet (ACDC)	27.5	Deep High-Resolution Representation Learning for Visual Recognition
MobileNetV2	16.05	MobileNetV2: Inverted Residuals and Linear Bottlenecks
MobileNetV3 (MobileNetV3small)	18.2	Searching for MobileNetV3
SETR (PUP, Transformer-Large)	31.8	Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
SegFormer (MiT-B3)	27.0	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
ResNet-101	23.60	Deep Residual Learning for Image Recognition
ERFNet	9.0	ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation
FDA	24.45	FDA: Fourier Domain Adaptation for Semantic Segmentation
EDCNet	32.04	Exploring Event-driven Dynamic Context for Accident Scene Segmentation
DeepLabV3+ (ACDC)	26.8	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Fast-SCNN	26.32	Fast-SCNN: Fast Semantic Segmentation Network
Trans4Trans	39.20	Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance
SETR (MLA, Transformer-Large)	30.4	Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
MMUDA	46.97	Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning
PSPNet (ResNet-101)	20.1	Pyramid Scene Parsing Network

0 of 28 row(s) selected.