Semantic Segmentation On Foodseg103
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
模型名称 | mIoU | Paper Title | Repository |
---|---|---|---|
FoodSAM | 46.4 | FoodSAM: Any Food Segmentation | - |
CCNet (ReLeM-ResNet-50) | 36.8 | A Large-Scale Benchmark for Food Image Segmentation | |
CCNet (ResNet-50) | 35.5 | CCNet: Criss-Cross Attention for Semantic Segmentation | |
SeTR-MLA (ViT-16/B) | 45.1 | Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers | |
SeTR-Naive (ViT-16/B) | 41.3 | Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers | |
Swin-Transformer (Swin-Small) | 41.6 | Swin Transformer: Hierarchical Vision Transformer using Shifted Windows | |
SeTR-Naive (ReLeM-ViT-16/B) | 43.9 | A Large-Scale Benchmark for Food Image Segmentation |
0 of 7 row(s) selected.