Semantic Segmentation
151개 벤치마크 · 논문 15,671편 · 이 태스크의 논문 보기 →
Benchmarks
ADE20K
NYU Depth v2
Cityscapes test
Cityscapes val
ADE20K val
PASCAL Context
S3DIS Area5
S3DIS
PASCAL VOC 2012 test
ScanNet
SUN-RGBD
DensePASS
PASCAL VOC 2012 val
DADA-seg
DeLiVER
Stanford2D3D Panoramic
BDD100K val
MCubeS
COCO-Stuff test
CamVid
ISPRS Potsdam
ImageNet-S
LaRS
LoveDA
iSAID
KITTI-360
Semantic3D
Trans10K
Dark Zurich
FMB Dataset
UrbanLF
Vaihingen
ISPRS Vaihingen
LIP val
Nighttime Driving
ZJU-RGB-P
EventScape
GTAV-to-Cityscapes Labels
ScanNetV2
Potsdam
US3D
BJRoad
Cityscapes
SYN-UDTIRI
SpaceNet 1
UAVid
DSEC
DDD17
DELIVER
SpectralWaste
INRIA Aerial Image Labeling
LLRGBD-synthetic
MCubeS (P)
Mapillary val
UPLight
FoodSeg103
KITTI Semantic Segmentation
Pothole Mix
SELMA
SYNTHIA-to-Cityscapes
SkyScapes-Dense
VDD
ACDC Scribbles
GAMUS
Porto
Stanford2D3D - RGBD
SynPASS
TLCGIS
Synthetic Bathing Perception
Hypersim
RELLIS-3D Dataset
Replica
ShapeNet
Toronto-3D L002
BIG
CC3M-TagMask
Matterport3D
PETRAW
Structured3D
THUD Robotic Dataset
SYNTHIA
CEMS-W
DIVA-HisDB
PASCAL VOC 2011 test
PASTIS
Potsdam
SIFT-flow
US3D
dacl10k v1 testdev
PASCAL VOC
38-Cloud
AI-TOD
ApolloScape
Cleargrasp (Novel)
Endoscapes
Freiburg Forest
Graz-02
HERA RFI Detection
HePIC 🏛️
Kvasir-Instrument
LOFAR RFI Detection
PASCAL VOC 2007
PH2
SYNTHIA-CVPR’16
SkyScapes-Lane
COCO-Stuff
LandCover.ai
AIRS
ARCH2S
ATLANTIS
BDD
COCO-Stuff full
COCO-Stuff-27
Cam2BEV
Cityscapes 3D
DeLiVER test
DroneDeploy
FP4S
HAM10000
ISIC 2017
ManipalUAVid
Mila Simulated Floods
MixedWM38
OpenEDS
PASCAL VOC 2010 test
PASCAL VOC 2011
PASCAL VOC 2012
PASTIS-R
RUGD
SBCoseg
STARE
SWIMSEG
SWINSEG
SWINySEG
SemanticPOSS
UTFPR-SBD3
WildDash
dacl10k v1 testfinal
uyfds
Most implemented
U-Net: Convolutional Networks for Biomedical Image Segmentation
Deep Residual Learning for Image Recognition
Mask R-CNN
MobileNetV2: Inverted Residuals and Linear Bottlenecks
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
MMDetection: Open MMLab Detection Toolbox and Benchmark
Papers
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. However, OVSS performance often degrades in…
Semantic SegmentationRGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation
In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations. RGBD20K possess…
Semantic SegmentationGTR: Gated Token Recurrence for Efficient Dense Prediction
Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Rec…
Monocular Depth EstimationInstance SegmentationSemantic SegmentationPose EstimationSSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion
This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring complex architectural redesigns. The fact is that, over the last years, SS…
Semantic SegmentationPoint CloudsPiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
With the increasing deployment of deep neural networks in critical systems, such as medical diagnostics and autonomous vehicles, ensuring their interpretability is crucial to building trust in decision-making systems. In…
Semantic SegmentationImage ClassificationObject LocalizationAutonomous VehiclesNeuroTS-Net: Multi-Class Semantic Segmentation of Pediatric Brain Tumors in Multi-Modal MRI
Pediatric brain tumors are a leading cause of cancer-related mortality in children, and their small, rare, and often low-contrast subregions make accurate manual delineation challenging. Reliable automated segmentation i…
Semantic Segmentation