Abstract | ||
---|---|---|
To alleviate the burden of manual image annotation, we propose an automatic learning method to enable object detection. This method mainly consists of the following three aspects: (1) a novel synthetic data generation strategy, which can automatically generate large-scale synthetic data with bounding-box annotations using only semantic concepts of target categories; (2) self-training paradigm combined with synthetic data generation strategy, which mines more information from the unannotated real data through iterative training to improve the performance of the object detector; (3) a simple and effective pseudo box filtering method, which can purify the quality of pseudo boxes during training. Without using any annotations (i.e., image-level annotations and bounding-box annotations) from the PASCAL VOC dataset, our proposed method can obtain 59.3% and 55.1% mAP on PASCAL VOC 2007 and PASCAL VOC 2012, respectively. We also demonstrate the effectiveness of our method on several datasets, including CUB-200–2011, FGVC Aircraft, Stanford Cars, Bird-Aircraft-Car-Dog, and CBCL StreetScenes. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.neucom.2022.02.012 | Neurocomputing |
Keywords | DocType | Volume |
Automatic learning,Object detection,Synthetic images,Pseudo boxes | Journal | 484 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiang Zhang | 1 | 0 | 0.34 |
Chao Zhao | 2 | 0 | 0.34 |
Hangzai Luo | 3 | 718 | 43.92 |
Wanqing Zhao | 4 | 15 | 7.07 |
Sheng Zhong | 5 | 2019 | 144.16 |
Lei Tang | 6 | 0 | 0.34 |
Jinye Peng | 7 | 284 | 40.93 |
Jianping Fan | 8 | 2677 | 192.33 |