Deep CNN Ensemble with Data Augmentation for Object Detection
By Jian Guo, Stephen Gould. 2015
63 citations recorded by the source corpus.
We report on the methods used in our recent DeepEnsembleCoco submission to the PASCAL VOC 2012 challenge, which achieves state-of-the-art performance on the object detection task. Our method is a variant of the R-CNN model proposed Girshick:CVPR14 with two key improvements to training and evaluation. First, our method constructs an ensemble of deep CNN models with different architectures that are complementary to each other. Second, we augment the PASCAL VOC training set with images from the Microsoft COCO dataset to significantly enlarge the amount training data. Importantly, we select a subset of the Microsoft COCO images to be consistent with the PASCAL VOC task. Results on the PASCAL VOC evaluation server show that our proposed method outperform all previous methods on the PASCAL VOC 2012 detection task at time of submission.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Judy Hoffman
- Saurabh Gupta
- Trevor Darrell
- Kate Saenko
- Sergey Levine
- Mingsheng Long
- Jianmin Wang
- Dacheng Tao
In Computer Vision and Pattern Recognition
- Trevor Darrell
- Luc Van Gool
- Judy Hoffman
- Jitendra Malik
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Abhinav Kumar Gupta
Citations in the corpus
- A survey of uncertainty in deep neural networks (2021, methodology): “Guo and Gould [233] used augmentation methods within in an ensemble approach for object detection.”
- Learning with Side Information through Modality Hallucination (2016, methodology): “For example, an ensemble of two ConvNets each initialized randomly and then trained using the same data source, outperforms either model independently [13].”