|
VPNeXt
|
VPNeXt -- Rethinking Dense Decoding for Plain Vis…
|
71.10
|
2025-02-23
|
|
|
PlainSeg (EVA-02-L)
|
Minimalist and High-Performance Semantic Segmenta…
|
71.00
|
2023-10-19
|
|
|
InternImage-H
|
InternImage: Exploring Large-Scale Vision Foundat…
|
70.30
|
2022-11-10
|
|
|
RSSeg-ViT-L (BEiT pretrain)
|
Representation Separation for Semantic Segmentati…
|
68.90
|
2022-12-28
|
|
|
ViT-Adapter-L (Mask2Former, BEiT pretrain)
|
Vision Transformer Adapter for Dense Predictions
|
68.20
|
2022-05-17
|
|
|
ViT-Adapter-L (UperNet, BEiT pretrain)
|
Vision Transformer Adapter for Dense Predictions
|
67.50
|
2022-05-17
|
|
|
RSSeg-ViT-L
|
Representation Separation for Semantic Segmentati…
|
67.50
|
2022-12-28
|
|
|
SegViT (ours)
|
SegViT: Semantic Segmentation with Plain Vision T…
|
65.30
|
2022-10-12
|
|
|
CAA + CAR (ConvNeXt-Large + JPU)
|
CAR: Class-aware Regularizations for Semantic Seg…
|
64.10
|
2022-03-14
|
|
|
SenFormer (Swin-L)
|
Efficient Self-Ensemble for Semantic Segmentation
|
64.00
|
2021-11-26
|
|
|
Sequential Ensemble (Segformer + HRNet)
|
Sequential Ensembling for Semantic Segmentation
|
62.10
|
2022-10-08
|
|
|
CAA + Simple decoder (Efficientnet-B7)
|
Channelized Axial Attention for Semantic Segmenta…
|
60.50
|
2021-01-19
|
|
|
DPT-Hybrid
|
Vision Transformers for Dense Prediction
|
60.46
|
2021-03-24
|
|
|
CAA (Efficientnet-B7)
|
Channelized Axial Attention for Semantic Segmenta…
|
60.10
|
2021-01-19
|
|
|
HRNetV2 + OCR + RMI (PaddleClas pretrained)
|
Segmentation Transformer: Object-Contextual Repre…
|
59.60
|
2019-09-24
|
|
|
Seg-L-Mask/16
|
Segmenter: Transformer for Semantic Segmentation
|
59.00
|
2021-05-12
|
|
|
ResNeSt-269
|
ResNeSt: Split-Attention Networks
|
58.90
|
2020-04-19
|
|
|
DEPICT-SA (ViT-L multi-scale)
|
Rethinking Decoders for Transformer-based Semanti…
|
58.60
|
2024-11-05
|
|
|
ResNeSt-200
|
ResNeSt: Split-Attention Networks
|
58.40
|
2020-04-19
|
|
|
DEPICT-SA (ViT-L single-scale)
|
Rethinking Decoders for Transformer-based Semanti…
|
57.90
|
2024-11-05
|
|
|
CondNet(ResNest-101)
|
CondNet: Conditional Classifier for Scene Segment…
|
57.00
|
2021-09-21
|
|
|
SenFormer (ResNet-101)
|
Efficient Self-Ensemble for Semantic Segmentation
|
56.60
|
2021-11-26
|
|
|
ResNeSt-101
|
ResNeSt: Split-Attention Networks
|
56.50
|
2020-04-19
|
|
|
OCR (HRNetV2-W48)
|
Segmentation Transformer: Object-Contextual Repre…
|
56.20
|
2019-09-24
|
|
|
GPaCo (ResNet101)
|
Generalized Parametric Contrastive Learning
|
56.20
|
2022-09-26
|
|
|
CondNet(ResNet-101)
|
CondNet: Conditional Classifier for Scene Segment…
|
56.00
|
2021-09-21
|
|
|
SETR-MLA (16, 80k, MS)
|
Rethinking Semantic Segmentation from a Sequence-…
|
55.83
|
2020-12-31
|
|
|
DCNAS
|
DCNAS: Densely Connected Neural Architecture Sear…
|
55.60
|
2020-03-26
|
|
|
DNL
|
Disentangled Non-Local Neural Networks
|
55.30
|
2020-06-11
|
|
|
HamNet (ResNet-101)
|
Is Attention Better Than Matrix Decomposition?
|
55.20
|
2021-09-09
|
|
|
CAA (ResNet-101)
|
Channelized Axial Attention for Semantic Segmenta…
|
55.00
|
2021-01-19
|
|
|
OCR (ResNet-101)
|
Segmentation Transformer: Object-Contextual Repre…
|
54.80
|
2019-09-24
|
|
|
SIW(Segformer-B5)
|
Scaling up Multi-domain Semantic Segmentation wit…
|
54.20
|
2022-02-04
|
|
|
CFNet (ResNet-101)
|
Deep High-Resolution Representation Learning for …
|
54.00
|
2019-08-20
|
|
|
HRNetV2 HRNetV2-W48
|
Deep High-Resolution Representation Learning for …
|
54.00
|
2019-08-20
|
|
|
CPN(ResNet-101)
|
Context Prior for Scene Segmentation
|
53.90
|
2020-04-03
|
|
|
LaU-regression-loss (ResNet-101)
|
Location-aware Upsampling for Semantic Segmentati…
|
53.90
|
2019-11-13
|
|
|
DGCNet (MS, ResNet-101)
|
Dual Graph Convolutional Network for Semantic Seg…
|
53.70
|
2019-09-13
|
|
|
BFP
|
Boundary-Aware Feature Propagation for Scene Segm…
|
53.60
|
2019-08-31
|
|
|
SVCNet (ResNet-101)
|
Semantic Correlation Promoted Shape-Variant Conte…
|
53.20
|
2019-09-05
|
|
|
Joint Pyramid Upsampling + EncNet
|
FastFCN: Rethinking Dilated Convolution in the Ba…
|
53.10
|
2019-03-28
|
|
|
EMANet
|
Expectation-Maximization Attention Networks for S…
|
53.10
|
2019-07-31
|
|
|
Asymmetric ALNN
|
Asymmetric Non-local Neural Networks for Semantic…
|
52.80
|
2019-08-21
|
|
|
CASSOD
|
CASSOD-Net: Cascaded and Separable Structures of …
|
52.76
|
2021-04-29
|
|
|
DANet (ResNet-101)
|
Dual Attention Network for Scene Segmentation
|
52.60
|
2018-09-09
|
|
|
DUpsampling
|
Decoders Matter for Semantic Segmentation: Data-D…
|
52.50
|
2019-03-05
|
|
|
EncNet (ResNet-101)
|
Context Encoding for Semantic Segmentation
|
51.70
|
2018-03-23
|
|
|
ResNet-38
|
Wider or Deeper: Revisiting the ResNet Model for …
|
48.10
|
2016-11-30
|
|
|
PSPNet (ResNet-101)
|
Pyramid Scene Parsing Network
|
47.80
|
2016-12-04
|
|
|
RefineNet
|
RefineNet: Multi-Path Refinement Networks for Hig…
|
47.30
|
2016-11-20
|
|
|
DeepLabV2
|
DeepLab: Semantic Image Segmentation with Deep Co…
|
45.70
|
2016-06-02
|
|
|
VeryDeep
|
Bridging Category-level and Instance-level Semant…
|
44.50
|
2016-05-23
|
|
|
Piecewise
|
Efficient piecewise training of deep structured m…
|
43.30
|
2015-04-04
|
|
|
Dilated-FCN2s
|
Efficient Yet Deep Convolutional Neural Networks …
|
42.60
|
2017-07-26
|
|
|
HO CRF
|
Higher Order Conditional Random Fields in Deep Ne…
|
41.30
|
2015-11-25
|
|
|
BoxSup
|
BoxSup: Exploiting Bounding Boxes to Supervise Co…
|
40.50
|
2015-03-05
|
|
|
ParseNet
|
ParseNet: Looking Wider to See Better
|
40.40
|
2015-06-15
|
|
|
CRF-RNN
|
Conditional Random Fields as Recurrent Neural Net…
|
39.30
|
2015-02-11
|
|
|
FCN-8s
|
Fully Convolutional Networks for Semantic Segment…
|
37.80
|
2014-11-14
|
|
|
CFM
|
Convolutional Feature Masking for Joint Object an…
|
34.40
|
2014-12-03
|
|
|
RBE2E
|
Region-based semantic segmentation with end-to-en…
|
32.50
|
2016-07-26
|
|
|
SegCLIP
|
SegCLIP: Patch Aggregation with Learnable Centers…
|
24.70
|
2022-11-27
|
|