miou
Mean Intersection over Union (mIoU) is a common evaluation metric used in tasks like image segmentation. It measures the overlap between predicted segments and the ground truth segments, where higher mIoU values indicate better segmentation accuracy.
- Exploring Structural Degradation in Dense Representations for Self-supervised Learning
- LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation
- Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance
- MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation
- Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation