TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Weakly Supervised Object Detection	MS COCO	ProNet	MAP	43.5	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pronet-learning-to-propose-object-specific/weakly-supervised-object-detection-on-coco)](https://paperswithcode.com/sota/weakly-supervised-object-detection-on-coco?p=pronet-learning-to-propose-object-specific)`

ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

CVPR 2016 · Chen Sun, Manohar Paluri, Ronan Collobert, Ram Nevatia, Lubomir Bourdev ·

This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.