Weakly Supervised Semantic Segmentation On 1

평가 지표

Mean IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Mean IoU	Paper Title	Repository
SFC(ResNet-101)	72.5	SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
URN(ResNet-101, no saliency, no RW)	69.7	Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation
PMM(Res2Net101, no saliency, no RW)	70.5	Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
ADELE (DeepLabV1-ResNet38)	72.0	Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
Infer-CAM(DeepLabV2-R101)	71.8	Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
SPML (DeepLabV2-R101)	71.6	Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning	-
QA-CLIMS	75.5	Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation
VWL-M	70.4	Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
ICAM	70.8	Importance Sampling CAMs for Weakly-Supervised Segmentation	-
EPS(DeepLabV1-ResNet101	71.8	Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
CLIP-ES(DeepLabV2-ResNet101)	73.9	CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
AMN (DeepLabV2-ResNet101, MS-COCO-pretrained weights)	70.6	Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
RIB+Sal (DeepLabV2-ResNet101)	70.0	Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
AMN (DeepLabV2-ResNet101)	69.6	Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
IRNet (ResNet-50)	64.8	Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
SLRNet(1-stage,ResNet38)	67.6	Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
ViT-PCM	70.9	Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
W-OoD (WResNet-38)	70.1	Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
ClusterCAM	70.7	Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
RCA	72.8	Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

0 of 60 row(s) selected.