Scale-aware Automatic Augmentation for Object Detection
arXiv:2103.17220
Abstract
We propose Scale-aware AutoAug to learn data augmentation policies for object detection. We define a new scale-aware search space, where both image- and box-level augmentations are designed for maintaining scale invariance. Upon this search space, we propose a new search metric, termed Pareto Scale Balance, to facilitate search with high efficiency. In experiments, Scale-aware AutoAug yields significant and consistent improvement on various object detectors (e.g., RetinaNet, Faster R-CNN, Mask R-CNN, and FCOS), even compared with strong multi-scale training baselines. Our searched augmentation policies are transferable to other datasets and box-level tasks beyond object detection (e.g., instance segmentation and keypoint estimation) to improve performance. The search cost is much less than previous automated augmentation approaches for object detection. It is notable that our searched policies have meaningful patterns, which intuitively provide valuable insight for human data augmentation design. Code and models will be available at https://github.com/Jia-Research-Lab/SA-AutoAug.
Accepted by CVPR 2021
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- Improved Regularization of Convolutional Neural Networks with Cutout
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- Bag of Freebies for Training Object Detection Neural Networks
- Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
- Data Augmentation in Emotion Classification Using Generative Adversarial Networks
- Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
- Empirical Upper Bound in Object Detection and More