Weakly Supervised Semantic Segmentation On 4

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
DHR (Swin-L, Mask2Former)56.8DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
SemPLeS (Swin-L)56.1Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation
WSSS-SAM(DeepLabV2-ResNet101)55.6An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
FMA-WSSS (Swin-L)55.4Foundation Model Assisted Weakly Supervised Semantic Segmentation
CoSA (SWIN-B, multi-stage)53.7Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation
CoSA (ViT-B, single-stage)51.1Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation
WeakTr (ViT-S, multi-stage)50.3WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
MARS (ResNet-101, multi-stage)49.4MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
WeakTr (DeiT-S, multi-stage)46.9WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
RS+EPM (ResNet-101, multi-stage)46.4RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
T2MDiffusion(DeepLabV2-ResNet101)45.7From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
FBR45.6Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
CLIP-ES(DeepLabV2-ResNet101)45.4CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
ACR(DeeplabV1-ResNet38)45.3Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor-
BECO(DeepLabV3Plus+R101)45.1Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation-
ACR-WSSS(DeepLabV2-ResNet101)45.0All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
ViT-PCM45.0Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
AMN (DeepLabV2-ResNet101)44.7Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
L2G (DeepLabV2-ResNet101)44.2L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
RIB (DeepLabV2-ResNet101, No Saliency)43.8Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
0 of 39 row(s) selected.
Weakly Supervised Semantic Segmentation On 4 | SOTA | HyperAI超神经