Semantic Segmentation on Vaihingen

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	CMX	82.87	No	CMX: Cross-Modal Fusion for RGB-X Semantic Segme...	2022-03-09	Code
2	LMFNet-2 (	82.49	No	LMFNet: An Efficient Multimodal Fusion Approach ...	2024-04-21	-
3	SA-Gate	81.03	No	Bi-directional Cross-Modality Feature Propagatio...	2020-07-17	Code
4	V-FuseNet	79.56	No	Beyond RGB: Very High Resolution Urban Remote Se...	2017-11-23	Code
5	UnetFormer	77.24	No	UNetFormer: A UNet-like Transformer for Efficien...	2021-09-18	Code
6	SegFormer-B1	76.92	No	SegFormer: Simple and Efficient Design for Seman...	2021-05-31	Code
7	PSPNet	76.79	No	Pyramid Scene Parsing Network	2016-12-04	Code
8	HRNet-48	76.75	No	Deep High-Resolution Representation Learning for...	2019-08-20	Code
9	SegFormer-B2	76.69	No	SegFormer: Simple and Efficient Design for Seman...	2021-05-31	Code
10	HRNet-18	75.9	No	Deep High-Resolution Representation Learning for...	2019-08-20	Code
11	SegFormer-B0	75.57	No	SegFormer: Simple and Efficient Design for Seman...	2021-05-31	Code
12	FPN	74.86	No	Feature Pyramid Networks for Object Detection	2016-12-09	Code
13	DeepLabV3+	72.9	No	Encoder-Decoder with Atrous Separable Convolutio...	2018-02-07	Code

#1CMXSOTA
82.87
mIoU· 2022-03-09
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers Code
#2LMFNet-2 (
82.49
mIoU· 2024-04-21
LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing
#3SA-GateSOTA
81.03
mIoU· 2020-07-17
Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation Code
#4V-FuseNetSOTA
79.56
mIoU· 2017-11-23
Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks Code
#5UnetFormer
77.24
mIoU· 2021-09-18
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery Code
#6SegFormer-B1
76.92
mIoU· 2021-05-31
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Code
#7PSPNetSOTA
76.79
mIoU· 2016-12-04
Pyramid Scene Parsing Network Code
#8HRNet-48
76.75
mIoU· 2019-08-20
Deep High-Resolution Representation Learning for Visual Recognition Code
#9SegFormer-B2
76.69
mIoU· 2021-05-31
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Code
#10HRNet-18
75.9
mIoU· 2019-08-20
Deep High-Resolution Representation Learning for Visual Recognition Code
#11SegFormer-B0
75.57
mIoU· 2021-05-31
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Code
#12FPN
74.86
mIoU· 2016-12-09
Feature Pyramid Networks for Object Detection Code
#13DeepLabV3+
72.9
mIoU· 2018-02-07
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation Code