How Trustworthy are Performance Evaluations for Basic Vision Tasks?
This addresses the issue of inconsistent algorithm rankings for researchers and practitioners in computer vision, though it is incremental as it builds on existing evaluation methods.
The paper tackles the problem of unreliable performance evaluations in basic vision tasks by proposing a notion of trustworthiness for criteria, requiring robustness, contextual meaningfulness, and consistency, and finds that many widely-used criteria fail these requirements.
This paper examines performance evaluation criteria for basic vision tasks involving sets of objects namely, object detection, instance-level segmentation and multi-object tracking. The rankings of algorithms by an existing criterion can fluctuate with different choices of parameters, e.g. Intersection over Union (IoU) threshold, making their evaluations unreliable. More importantly, there is no means to verify whether we can trust the evaluations of a criterion. This work suggests a notion of trustworthiness for performance criteria, which requires (i) robustness to parameters for reliability, (ii) contextual meaningfulness in sanity tests, and (iii) consistency with mathematical requirements such as the metric properties. We observe that these requirements were overlooked by many widely-used criteria, and explore alternative criteria using metrics for sets of shapes. We also assess all these criteria based on the suggested requirements for trustworthiness.