Optimizing Average Precision Using Weakly Supervised Data

  title={Optimizing Average Precision Using Weakly Supervised Data},
  author={Aseem Behl and C. V. Jawahar and M. Pawan Kumar},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
Many tasks in computer vision, such as action classification and object detection, require us to rank a set of samples according to their relevance to a particular visual category. The performance of such tasks is often measured in terms of the average precision (AP). Yet it is common practice to employ the support vector machine (SVM) classifier, which optimizes a surrogate 0-1 loss. The popularity of SVM can be attributed to its empirical performance. Specifically, in fully supervised… CONTINUE READING