Semantic Segmentation
Semantic segmentation is a task in the field of computer vision that aims to classify each pixel in an image into a specific category or object. Its goal is to generate a dense pixel-level segmentation map where each pixel is assigned to a particular category or object. This task has significant application value in areas such as autonomous driving and medical image analysis, and is typically evaluated using metrics like Mean Intersection over Union (Mean IoU) and Pixel Accuracy.
Cloud-Net+
ScribFormer
ONE-PEACE
SeMask (SeMask Swin-L MSFaPN-Mask2Former)
Unet++(ResNet-50)
ICT-Net
ERFNet-IntRA-KD (ours)
BIM-Net
Erfani et al.
FasterSeg
SERNet-Former_v2
PSPNet + CascadePSP
uNetXST
SERNet-Former
UPerNet (RN50)
VLTSeg
SPFNet34M
SERNet-Former
EfficientSeg
Cleargrasp
Deeplab v2
DiffSeg (512)
SegFormer-B5 (Single Scale)
FPN EfficientNet-B4
MMUDA
Refign (HRDA)
CAFuser-CAA
GeminiFusion
Trans4PASS (multi-scale)
U-Net
DLv3+ (Xception65)
CMNeXt
MoCo V2 Surg SSL - DeepLabv3+ head
Bimodal SegNet
Ensemble-04 MiT-0 MiT-1 RNX-1 RNX-2
MMSFormer (RGB-Infrared)
FoodSAM
Unet+RN34
FP4S
SSMA
TIMF
VOLO-D5
MFSNet
TEC (ViT-B/16, 224x224, SSL+FT, mmseg)
UANet(PVT-V2-B2)
SegNeXt-L
AerialFormer-B
LSKNet-T
CMX (RGB-Depth)
RPVNet [xu2021rpvnet]
DoubleUNet
KNet (Swin-T)
SOLIDER
SMMCL (SegNeXt-B)
Nearest Latent Neighbours
UNet3D
UNetFormer
UVid-Net
AO-SegNet
SFSS-MMSI (RGB+Depth)
StitchFusion (RGB-A-D-N)
ShareCMP (B2 RGB-A-D)
WaferSegClassNet
TADP
DiffusionMMS (DAT++-S)
RITnet
SenFormer (Swin-L)
SegCLIP
GALDNet
Plugin network
WASPnet-CRF (ours)
EfficientNet-L2+NAS-FPN (single scale test, with self-training)
U-TAE
MobileUNETR
CMNeXt
HCMUS-CPS-DLU-Net
GA-Nav
LabelMaker
GA-Nav
Sonata + PTv3
PointNet
Floors are Flat
CMX
Feature Geometric Net
SGPN
RBE2E
MAE+MTP(ViT-L)
CMX (RGB-HYPER)
Trans4PASS+ (Supervised + Small + MS)
UNet
GeminiFusion (Swin-Large)
ACLNet
Trans4PASS+
CGA-Net
SSMA
HRDA + PiPa
SA-Gate
SA-Gate
EyeNet
Trans4Trans (M)
LSKNet-S
ShareCMP (B2 RGB-FP)
CMNeXt (RGB-LF80)
HRNet-48
EPYNET
Segformer-B2
ShareCMP (B4 RGB-FP)