Many state-of-the-art approaches for object recognition

reduce the problem to a 0-1 classifi cation task. Such re-

ductions allow one to leverage sophisticated classifi ers for

learning. These models are typically trained independently

for each class using positive and negative examples cropped

from images. At test-time, various post-processing heuris-

tics such as non-maxima suppression (NMS) are required

to reconcile multiple detections within and between differ-

ent classes for each image. Though crucial to good perfor-

mance on benchmarks, this post-processing is usually de-

fi ned heuristically.-Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. Such re-ductions allow one to leverage sophisticated classifiers for learning. These models are typically trained independently for each class using positive and negative examples cropped from images. At test-time, various post-processing heuris-tics such as non-maxima suppression (NMS) are required to reconcile multiple detections within and between differ-ent classes for each image. Though crucial to good perfor-mance on benchmarks, this post-processing is usually de-fined heuristically.