Mixup Regularization for Region Proposal based Object Detectors
arXiv:2003.02065
Abstract
Mixup - a neural network regularization technique based on linear interpolation of labeled sample pairs - has stood out by its capacity to improve model's robustness and generalizability through a surprisingly simple formalism. However, its extension to the field of object detection remains unclear as the interpolation of bounding boxes cannot be naively defined. In this paper, we propose to leverage the inherent region mapping structure of anchors to introduce a mixup-driven training regularization for region proposal based object detectors. The proposed method is benchmarked on standard datasets with challenging detection settings. Our experiments show an enhanced robustness to image alterations along with an ability to decontextualize detections, resulting in an improved generalization power.
References in corpus (12)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- YOLOv3: An Incremental Improvement
- A systematic study of the class imbalance problem in convolutional neural networks
- Interpolation Consistency Training for Semi-Supervised Learning
- Opening the Black Box of Deep Neural Networks via Information
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Regularization for Deep Learning: A Taxonomy
- Bag of Freebies for Training Object Detection Neural Networks
- Augmenting Data with Mixup for Sentence Classification: An Empirical Study
- On Physical Adversarial Patches for Object Detection
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks