Semi Supervised Semantic Segmentation On 35
평가 지표
Validation mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Validation mIoU | Paper Title | Repository |
|---|---|---|---|
| AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 74.28 | Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | |
| Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) | 66.97 | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | |
| Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single-pass eval) | 65.81 | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks |
0 of 3 row(s) selected.