HyperAI

Semantic Segmentation On Ade20K

المقاييس

GFLOPs
Params (M)
Validation mIoU

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
GFLOPs
Params (M)
Validation mIoU
Paper TitleRepository
InternImage-L252625654.1InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
TEC (Vit-B, Upernet)--51.0Towards Sustainable Self-supervised Learning
EfficientViT-B3 (r512)--49EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
VAN-Large-4948.1Visual Attention Network
MaskFormer(Swin-B)--53.8Per-Pixel Classification is Not All You Need for Semantic Segmentation
CFNet(ResNet-101)--44.89Co-Occurrent Features in Semantic Segmentation
ConvNeXt-S-8249.6A ConvNet for the 2020s
SegNet--21.64SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
M3I Pre-training (InternImage-H)-131062.9Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
HRViT-b2 (SegFormer, SS)-20.848.76Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
SwinV2-G-HTC++ Liu et al. ([2021a])--53.7Swin Transformer V2: Scaling Up Capacity and Resolution
SETR-MLA (160k, MS)--50.28Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
ELSA-Swin-S--50.3ELSA: Enhanced Local Self-Attention for Vision Transformer
Sequential Ensemble (DeepLabv3+)--46.8Sequential Ensembling for Semantic Segmentation-
FastViT-SA36---FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
ACNet (ResNet-101)--45.90Adaptive Context Network for Scene Parsing-
SGR (ResNet-101)--44.32Symbolic Graph Reasoning Meets Convolutions
ConvMLP-S--35.8ConvMLP: Hierarchical Convolutional MLPs for Vision
SeMask (SeMask Swin-L MSFaPN-Mask2Former)--58.2SeMask: Semantically Masked Transformers for Semantic Segmentation
ConvMLP-M--38.6ConvMLP: Hierarchical Convolutional MLPs for Vision
0 of 230 row(s) selected.