Discriminative models for multi-class object layout

摘要: Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. Such reductions allow one leverage sophisticated classifiers learning. These models are typically trained independently each class using positive and negative examples cropped from images. At test-time, various post-processing heuristics such as non-maxima suppression (NMS) required reconcile multiple detections within between different classes image. Though crucial good performance on benchmarks, this is usually defined heuristically.