Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data

21 Jun 2014  ·  Rushil Anirudh, Pavan Turaga ·

In this paper, we study the problem of `test-driving' a detector, i.e. allowing a human user to get a quick sense of how well the detector generalizes to their specific requirement. To this end, we present the first system that estimates detector performance interactively without extensive ground truthing using a human in the loop. We approach this as a problem of estimating proportions and show that it is possible to make accurate inferences on the proportion of classes or groups within a large data collection by observing only $5-10\%$ of samples from the data. In estimating the false detections (for precision), the samples are chosen carefully such that the overall characteristics of the data collection are preserved. Next, inspired by its use in estimating disease propagation we apply pooled testing approaches to estimate missed detections (for recall) from the dataset. The estimates thus obtained are close to the ones obtained using ground truth, thus reducing the need for extensive labeling which is expensive and time consuming.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here