Joint calibration of Ensemble of Exemplar SVMs
This work addresses calibration for object detection models, but appears incremental as it builds on existing EE-SVM and CNN descriptor frameworks.
The paper tackles the problem of calibrating Ensemble of Exemplar SVMs by proposing a joint optimization method instead of independent calibration, resulting in improved window classification and object detection performance on ILSVRC 2014 and PASCAL VOC 2007 datasets.
We present a method for calibrating the Ensemble of Exemplar SVMs model. Unlike the standard approach, which calibrates each SVM independently, our method optimizes their joint performance as an ensemble. We formulate joint calibration as a constrained optimization problem and devise an efficient optimization algorithm to find its global optimum. The algorithm dynamically discards parts of the solution space that cannot contain the optimum early on, making the optimization computationally feasible. We experiment with EE-SVM trained on state-of-the-art CNN descriptors. Results on the ILSVRC 2014 and PASCAL VOC 2007 datasets show that (i) our joint calibration procedure outperforms independent calibration on the task of classifying windows as belonging to an object class or not; and (ii) this improved window classifier leads to better performance on the object detection task.