Abstract | ||
---|---|---|
Learning a satisfactory object detector generally requires sufficient training data to cover the most variations of the object. In this paper, we show that the performance of object detector is severely degraded when training examples are limited. We propose an approach to handle this issue by exploring a set of pretrained auxiliary detectors for other categories. By mining the global and local relationships between the target object category and auxiliary objects, a robust detector can be learned with very few training examples. We adopt the deformable part model proposed by Felzenszwalb and simultaneously explore the root and part filters in the auxiliary object detectors under the guidance of the few training examples from the target object category. An iterative solution is introduced for such a process. The extensive experiments on the PASCAL VOC 2007 challenge data set show the encouraging performance of the new detector assembled from those related auxiliary detectors. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/TIP.2011.2158231 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
local relationship mining,assemble new object detector,auxiliary object,deformable part model,learning (artificial intelligence),satisfactory object detector,robust detector,part filter,object detector,related auxiliary detector,new detector,pascal voc 2007 challenge data set,pretrained auxiliary object detector,pretrained auxiliary detector,adaptation,root filter,object detection,assemble,auxiliary object detector,global relationship mining,training example,target object category,training data,algorithm design,computer vision,algorithm design and analysis,learning artificial intelligence,detectors | Training set,Object detection,Computer vision,Algorithm design,Method,Computer science,Artificial intelligence,Detector,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 12 | 1941-0042 |
Citations | PageRank | References |
8 | 0.49 | 25 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kuiyuan Yang | 1 | 435 | 24.67 |
Meng Wang | 2 | 8 | 0.49 |
Xian-Sheng Hua | 3 | 6566 | 328.17 |
Shuicheng Yan | 4 | 767 | 25.71 |
Hong-Jiang ZHANG | 5 | 17378 | 1393.22 |