Enhancing Model Assessment in Vision-based Interactive Machine Teaching through Real-time Saliency Map Visualization
This addresses the issue for users of vision-based interactive machine teaching systems who need better model behavior understanding, though it is incremental as it adds visualization to existing methods.
The paper tackles the problem of insufficient feedback in interactive machine teaching systems by introducing real-time saliency map visualization to show which image regions the model uses for classification, helping users correct concepts iteratively.
Interactive Machine Teaching systems allow users to create customized machine learning models through an iterative process of user-guided training and model assessment. They primarily offer confidence scores of each label or class as feedback for assessment by users. However, we observe that such feedback does not necessarily suffice for users to confirm the behavior of the model. In particular, confidence scores do not always offer the full understanding of what features in the data are used for learning, potentially leading to the creation of an incorrectly-trained model. In this demonstration paper, we present a vision-based interactive machine teaching interface with real-time saliency map visualization in the assessment phase. This visualization can offer feedback on which regions of each image frame the current model utilizes for classification, thus better guiding users to correct the corresponding concepts in the iterative teaching.