TIDE: A General Toolbox for Identifying Object Detection Errors
This provides a general toolbox for researchers and practitioners to better understand and improve object detection models, though it is incremental as it builds on existing error analysis methods.
The authors tackled the problem of analyzing error sources in object detection and instance segmentation by introducing TIDE, a framework that segments errors into six types and measures each error's contribution to overall performance, demonstrating its utility across 4 datasets and 7 models.
We introduce TIDE, a framework and associated toolbox for analyzing the sources of error in object detection and instance segmentation algorithms. Importantly, our framework is applicable across datasets and can be applied directly to output prediction files without required knowledge of the underlying prediction system. Thus, our framework can be used as a drop-in replacement for the standard mAP computation while providing a comprehensive analysis of each model's strengths and weaknesses. We segment errors into six types and, crucially, are the first to introduce a technique for measuring the contribution of each error in a way that isolates its effect on overall performance. We show that such a representation is critical for drawing accurate, comprehensive conclusions through in-depth analysis across 4 datasets and 7 recognition models. Available at https://dbolya.github.io/tide/