Semantic Segmentation On Pascal Voc 2012 Val

Metriken

mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	mIoU	Paper Title	Repository
DeepLabv3-JFT	82.7%	Rethinking Atrous Convolution for Semantic Image Segmentation
RRM	66.3	Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach
FastDenseNas-arch1	77.1%	Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
SID	-	Simple Does It: Weakly Supervised Instance and Semantic Segmentation	-
SpineNet-S143 (single-scale test)	85.64%	Dilated SpineNet for Semantic Segmentation	-
FastDenseNas-arch2	77.3%	Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
PRM	53.4%	Weakly Supervised Instance Segmentation using Class Peak Response
Auto-DeepLab-L	82.04%	Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
HyperSeg-L	80.61%	HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
SSDD	64.9	Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
PSA w/ EADER DeepLab (Xception-65)	62.8%	Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation
FastDenseNas-arch0	78.0%	Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
ReLICv2	77.9%	Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Eff-B7 NAS-FPN (Copy-Paste pre-training, single-scale))	86.6%	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
BYOL	75.7%	Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
SIW	65%	Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings	-
G2	55.7%	Exploiting saliency for object segmentation from image level labels	-
DetCon	77.3%	Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
DeepLabv3 (ImageNet+300M)	76.5%	Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
TADP	87.11%	Text-image Alignment for Diffusion-based Perception

0 of 29 row(s) selected.