Improve Object Detection by Data Enhancement based on Generative Adversarial Nets
This work addresses the problem of enhancing object detection performance for computer vision practitioners by providing an incremental data augmentation technique to improve training efficiency.
The paper tackles the problem of improving object detection accuracy by addressing insufficient anchor box training due to limited ground truth boxes or invariant objects, proposing a data enhancement method based on foreground-background separation and GANs that perturbs images with color changes, salt noise, and contrast enhancement. The method achieves 78.7% mAP on PASCAL VOC2007 and 76.6% mAP on PASCAL VOC2012 with DSSD detection.
The accuracy of the object detection model depends on whether the anchor boxes effectively trained. Because of the small number of GT boxes or object target is invariant in the training phase, cannot effectively train anchor boxes. Improving detection accuracy by extending the dataset is an effective way. We propose a data enhancement method based on the foreground-background separation model. While this model uses a binary image of object target random perturb original dataset image. Perturbation methods include changing the color channel of the object, adding salt noise to the object, and enhancing contrast. The main contribution of this paper is to propose a data enhancement method based on GAN and improve detection accuracy of DSSD. Results are shown on both PASCAL VOC2007 and PASCAL VOC2012 dataset. Our model with 321x321 input achieves 78.7% mAP on the VOC2007 test, 76.6% mAP on the VOC2012 test.