Few-Example Object Detection with Model Communication

26 Jun 2017  ·  Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng ·

In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named "few-example object detection". The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, easy samples are generated first and, then the poorly initialized model undergoes improvement. As the model becomes more discriminative, challenging but reliable samples are selected. After that, another round of model improvement takes place. To further improve the precision and recall of the generated training samples, we embed multiple detection models in our framework, which has proven to outperform the single model baseline and the model ensemble method. Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly Supervised Object Detection ImageNet MSLPD MAP 13.9 # 3
Weakly Supervised Object Detection MS COCO MSLPD MAP 56.6 # 1
Weakly Supervised Object Detection PASCAL VOC 2007 MSLPD MAP 41.7 # 34
Weakly Supervised Object Detection PASCAL VOC 2012 test MSLPD MAP 35.4 # 30

Methods


No methods listed for this paper. Add relevant methods here