Successful visual object recognition methods typically rely on training datasets containing lots of richly annotated images. Annotating object bounding boxes is both expensive and subjective. We describe a weakly supervised convolutional neural network (CNN) for object recognition that does not rely on detailed object annotation and yet returns 86.3% mAP on the Pascal VOC classification task, outperforming previous fully-supervised systems by a sizable margin. Despite the lack of bounding box supervision, the network produces maps that clearly localize the objects in cluttered scenes. We also show that adding fully supervised object examples to our weakly supervised setup does not increase the classification performance.