Command Palette
Search for a command to run...
J&F Score
Date
J&F Score (Jaccard and F-measure Score) is one of the most essential evaluation metrics for video object segmentation (VOS) tasks in computer vision. This metric is the average of region similarity J (i.e., the Jaccard similarity coefficient / IoU) and boundary contour F-measure. It simultaneously balances the model’s pixel coverage within the target and boundary contour accuracy, providing a comprehensive reflection of the algorithm’s segmentation performance across the entire temporal sequence. It is usually reported as a percentage or a score between 0 and 1. This metric is widely used in relevant benchmarks and papers, and can effectively reflect model performance in this dimension. Higher values are better.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.