Command Palette

Search for a command to run...

Weakly Supervised Semantic Segmentation On 1

评估指标

Mean IoU

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
SemPLeS (Swin-L)82.9Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation
DHR (Swin-L, Mask2Former)82.3DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
FMA-WSSS (Swin-L)81.6Foundation Model Assisted Weakly Supervised Semantic Segmentation
WeakTr (ViT-S, multi-stage)79.0WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
MARS (ResNet-101, multi-stage)77.2MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
WSSS-SAM(DeepLabV2-ResNet101)77.1An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
QA-CLIMS75.5Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation
ISIM (ResNeSt-200)74.98ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
FBR74.9Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
HSC74.5Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation-
T2MDiffusion(DeepLabV2-ResNet101)74.2From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
WeakTr (DeiT-S, multi-stage)74.1WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
CLIP-ES(DeepLabV2-ResNet101)73.9CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
RS+EPM (ResNet-101, multi-stage)73.6RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
BECO(DeepLabV3Plus+MiT-B2)73.5Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation-
PPC (w/ EPS)73.5Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
L2G (ResNet101, DeepLab-LargeFOV)73.0L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
ORANDNet72.9Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
RCA72.8Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation
SFC(ResNet-101)72.5SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
0 of 60 row(s) selected.
Weakly Supervised Semantic Segmentation On 1 | SOTA | HyperAI超神经