Command Palette
Search for a command to run...

摘要
场景解析在开放词汇且场景多样化的无限制环境下极具挑战性。本文通过提出金字塔场景解析网络(PSPNet),结合基于多区域的上下文聚合机制,利用金字塔池化模块挖掘全局上下文信息,充分发挥其优势。所提出的全局先验表示方法在场景解析任务中表现出色,能够生成高质量的分割结果;而PSPNet则为像素级预测任务提供了一个优越的框架。该方法在多个公开数据集上均取得了当前最优性能,在2016年ImageNet场景解析挑战赛、PASCAL VOC 2012基准测试以及Cityscapes基准测试中均获得第一名。仅使用单一PSPNet模型,就在PASCAL VOC 2012上取得了85.4%的mIoU(平均交并比)新纪录,在Cityscapes上达到了80.2%的准确率新纪录。
代码仓库
leemathew1998/GradientWeight
pytorch
GitHub 中提及
manideep2510/eye-in-the-sky
tf
GitHub 中提及
udacity/MLND-CN-Capstone-TGSImage
GitHub 中提及
PaddlePaddle/PaddleSeg
paddle
qubvel/segmentation_models
tf
GitHub 中提及
PRBonn/bonnet
tf
GitHub 中提及
jqueguiner/image-segmentation
GitHub 中提及
kazuto1011/pspnet-pytorch
pytorch
GitHub 中提及
mdt48/semantic-segmentation-pytorch
pytorch
GitHub 中提及
daveboat/spp
pytorch
GitHub 中提及
tejaswigowda/semseg-pytorch
pytorch
GitHub 中提及
HenonBamboo/PSPNet-MindSpore
mindspore
GitHub 中提及
oandrienko/fast-semantic-segmentation
tf
GitHub 中提及
intelligent-vehicles/bevdriver
pytorch
GitHub 中提及
kdhingra307/temp
pytorch
GitHub 中提及
UBC-CIC/COVID19-L3-Net
pytorch
GitHub 中提及
branislavhesko/segmentation_framework
pytorch
GitHub 中提及
MS-Mind/MS-Code-06/tree/main/PSPNet
mindspore
DiMarzioRock7/Aerial-Semantic-Segmentation-Drone
pytorch
GitHub 中提及
mattangus/fast-semantic-segmentation
tf
GitHub 中提及
Rintarooo/PSPNet
pytorch
GitHub 中提及
switchablenorms/SwitchNorm_Segmentation
pytorch
GitHub 中提及
leemathew1998/RG
pytorch
GitHub 中提及
AnirudhAchal/Human-Parsing
pytorch
GitHub 中提及
cioppaanthony/rt-sbs
pytorch
GitHub 中提及
kukby/Mish-semantic-segmentation-pytorch
pytorch
GitHub 中提及
tensorflow/models
tf
GitHub 中提及
y-ouali/pytorch_segmentation
pytorch
Lxrd-AJ/Advanced_ML
pytorch
GitHub 中提及
osmr/imgclsmob
mxnet
GitHub 中提及
hszhao/PSPNet
官方
pytorch
GitHub 中提及
EvaBr/AnatomyNets
pytorch
GitHub 中提及
Media-Smart/vedaseg
pytorch
cj-mclaughlin/segmentation_research
tf
GitHub 中提及
BOBrown/deeparsing-master
GitHub 中提及
open-mmlab/mmsegmentation
pytorch
Mind23-2/MindCode-5/tree/main/PSPNet
mindspore
Rosie-Brigham/sesmeg
pytorch
GitHub 中提及
kannyjyk/Nested-UNet
tf
GitHub 中提及
holyseven/PSPNet-TF-Reproduce
tf
GitHub 中提及
YininKorea/Contour-aware-equipotential-learning
pytorch
GitHub 中提及
CSAILVision/semantic-segmentation-pytorch
pytorch
GitHub 中提及
DiMarzioRock7/PSPNet
pytorch
GitHub 中提及
PhanTom2003/PSPnet
pytorch
GitHub 中提及
RituYadav92/Image-segmentation
pytorch
GitHub 中提及
Mind23-2/MindCode-63
mindspore
GitHub 中提及
DoTung-bkhn/multiclass-segmentation
tf
GitHub 中提及
jqueguiner/camembert-as-a-service
pytorch
GitHub 中提及
yangyucheng000/PSPNet
mindspore
GitHub 中提及
irfanICMLL/structure_knowledge_distillation
pytorch
GitHub 中提及
warmspringwinds/pytorch-segmentation-detection
pytorch
GitHub 中提及
2023-MindSpore-1/ms-code-46
mindspore
GitHub 中提及
ZFTurbo/segmentation_models_3D
tf
GitHub 中提及
163GitHub/AI
pytorch
GitHub 中提及
tensorflow/models/tree/master/research/deeplab
tf
GitHub 中提及
burakalperen/Pytorch-Semantic-Segmentation
pytorch
GitHub 中提及
kingcong/PSPNet
mindspore
GitHub 中提及
fenglian425/Agriculture_AI
pytorch
GitHub 中提及
geekswaroop/Human-Parsing
pytorch
GitHub 中提及
基准测试
| 基准 | 方法 | 指标 | 
|---|---|---|
| dichotomous-image-segmentation-on-dis-te1 | PSPNet | E-measure: 0.791 HCE: 267 MAE: 0.089 S-Measure: 0.725 max F-Measure: 0.645 weighted F-measure: 0.557  | 
| dichotomous-image-segmentation-on-dis-te2 | PSPNet | E-measure: 0.828 HCE: 586 MAE: 0.092 S-Measure: 0.763 max F-Measure: 0.724 weighted F-measure: 0.636  | 
| dichotomous-image-segmentation-on-dis-te3 | PSPNet | E-measure: 0.843 HCE: 1111 MAE: 0.092 S-Measure: 0.774 max F-Measure: 0.747 weighted F-measure: 0.657  | 
| dichotomous-image-segmentation-on-dis-te4 | PSPNet | E-measure: 0.815 HCE: 3806 MAE: 0.107 S-Measure: 0.758 max F-Measure: 0.725 weighted F-measure: 0.630  | 
| dichotomous-image-segmentation-on-dis-vd | PSPNet | E-measure: 0.802 HCE: 1588 MAE: 0.102 S-Measure: 0.744 max F-Measure: 0.691 weighted F-measure: 0.603  | 
| lesion-segmentation-on-anatomical-tracings-of-1 | PSPNet | Dice: 0.3571 IoU: 0.254 Precision: 0.4769 Recall: 0.3335  | 
| real-time-semantic-segmentation-on-camvid | PSPNet | Frame (fps): 5.4 Time (ms): 185.0  | 
| real-time-semantic-segmentation-on-nyu-depth-1 | PSPNet101 | Speed(ms/f): 72 mIoU: 43.2  | 
| real-time-semantic-segmentation-on-nyu-depth-1 | PSPNet50 | Speed(ms/f): 47 mIoU: 41.8  | 
| real-time-semantic-segmentation-on-nyu-depth-1 | PSPNet18 | Speed(ms/f): 19 mIoU: 35.9  | 
| semantic-segmentation-on-ade20k | PSPNet (ResNet-101) | Validation mIoU: 43.29  | 
| semantic-segmentation-on-ade20k | PSPNet (ResNet-152) | Validation mIoU: 43.51  | 
| semantic-segmentation-on-ade20k | PSPNet | Test Score: 55.38 Validation mIoU: 44.94  | 
| semantic-segmentation-on-ade20k-val | PSPNet (ResNet-101) | mIoU: 43.29%  | 
| semantic-segmentation-on-ade20k-val | PSPNet (ResNet-152) | mIoU: 43.51%  | 
| semantic-segmentation-on-bdd100k-val | PSPNet | mIoU: 62.3  | 
| semantic-segmentation-on-cityscapes | PSPNet | Mean IoU (class): 78.4%  | 
| semantic-segmentation-on-cityscapes | PSPNet++ | Mean IoU (class): 80.2%  | 
| semantic-segmentation-on-cityscapes-val | PSPNet (Dilated-ResNet-101) | mIoU: 79.7  | 
| semantic-segmentation-on-dada-seg | PSPNet (ResNet-101) | mIoU: 20.1  | 
| semantic-segmentation-on-densepass | PSPNet (ResNet-50) | mIoU: 29.5%  | 
| semantic-segmentation-on-pascal-context | PSPNet (ResNet-101) | mIoU: 47.8  | 
| semantic-segmentation-on-pascal-voc-2012 | PSPNet | Mean IoU: 85.4%  | 
| semantic-segmentation-on-pascal-voc-2012 | PSPNet (ResNet-101) | Mean IoU: 82.6%  | 
| semantic-segmentation-on-potsdam | PSPNet | mIoU: 82.98  | 
| semantic-segmentation-on-scannetv2 | PSPNet | Mean IoU: 47.5%  | 
| semantic-segmentation-on-selma | PSPNet | mIoU: 68.4  | 
| semantic-segmentation-on-trans10k | PSPNet | GFLOPs: 187.03 mIoU: 68.23%  | 
| semantic-segmentation-on-urbanlf | PSPNet | mIoU (Real): 76.34 mIoU (Syn): 75.78  | 
| semantic-segmentation-on-us3d | PSNet | mIoU: 73.12  | 
| semantic-segmentation-on-vaihingen | PSPNet | mIoU: 76.79  | 
| thermal-image-segmentation-on-mfn-dataset | PSPNet | mIOU: 46.1  | 
| video-semantic-segmentation-on-camvid | PSPNet-50 | Mean IoU: 76  | 
| video-semantic-segmentation-on-cityscapes-val | PSPNet-101 [20] | mIoU: 79.7  | 
| video-semantic-segmentation-on-cityscapes-val | PSPNet-50 [20] | mIoU: 78.1  |