PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

9 Jul 2018  ·  Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, Alan Yuille ·

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that transfer the object detection problem to an image classification problem using Multiple Instance Learning (MIL), our strategy generates proposal clusters to learn refined instance classifiers by an iterative process. The proposals in the same cluster are spatially adjacent and associated with the same object. This prevents the network from concentrating too much on parts of objects instead of whole objects. We first show that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then show that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method. The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one. Experiments are conducted on the PASCAL VOC, ImageNet detection, and MS-COCO benchmarks for WSOD. Results show that our method outperforms the previous state of the art significantly.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly Supervised Object Detection ImageNet PCL-OB-G-Ens + FRCNN MAP 19.6 # 1
Weakly Supervised Object Detection PASCAL VOC 2007 PCL-OB-G-Ens + FRCNN MAP 48.8 # 22
Weakly Supervised Object Detection PASCAL VOC 2012 test PCL-OB-G-Ens + FRCNN MAP 44.2 # 20

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Weakly Supervised Object Detection Charades PCL MAP 2.83 # 2
Weakly Supervised Object Detection HICO-DET PCL MAP 3.62 # 2

Methods


No methods listed for this paper. Add relevant methods here