# Deep CNN Ensemble with Data Augmentation for Object Detection

arXiv: https://arxiv.org/abs/1506.07224 · HTML: https://mlsanity.com/paper/1506.07224/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2015.

## Built on by (most cited first, 10 of 10)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training](https://mlsanity.com/paper/2409.04707/) (2024)
- [REx: Data-Free Residual Quantization Error Expansion](https://mlsanity.com/paper/2203.14645/) (2022)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Classification of Colorectal Cancer Polyps via Transfer Learning and Vision-Based Tactile Sensing](https://mlsanity.com/paper/2211.04573/) (2022)
- [Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications](https://mlsanity.com/paper/2302.01440/) (2023)
- [What augmentations are sensitive to hyper-parameters and why?](https://mlsanity.com/paper/2111.03861/) (2021)
- [PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions](https://mlsanity.com/paper/2311.15806/) (2023)
- [Domain-Specialized Object Detection via Model-Level Mixtures of Experts](https://mlsanity.com/paper/2604.18256/) (2026)

## Abstract (arXiv)

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.