CorrectMe: An Interactive Framework for Human-in-the-Loop Correction and Explanation of Object Detection Models

Object detection models, while achieving greater performance, often suffer from recurring errors such as misclassifications or missed detections. Existing explainable AI (XAI) tools primarily offer static, observation-based explanations and rarely support interactive correction or retraining, especially for non-expert users. To bridge this gap, we introduce CorrectMe, an interactive framework that integrates human-in-the-loop correction and explanation into object detection workflows. CorrectMe empowers users to iteratively explore, interpret, and rectify model errors through a unified interface featuring semantic embedding visualizations, saliency-based explanations, and natural language rationales. Users can revise predictions and incrementally retrain the model, streamlining the refinement process through lightweight updates rather than full-scale retraining or annotation. Through application scenarios and user studies, we demonstrate that CorrectMe enables more strategic corrections, improves model understanding, and lowers the barrier to practical refinement of object detection models.