Is there any plan to support autoaugment?
Created by: sbl1996
AutoAugment[1] is effective to improve performance for object detection as shown in NAS-FPN, EfficientDet[2], and competitions[3]. Do you have any plans to support it? The official TensorFlow implementation is here.
[1] Zoph, Barret et al. “Learning Data Augmentation Strategies for Object Detection.” ArXiv abs/1906.11172 (2019): n. pag. [2] Tan, Mingxing et al. “EfficientDet: Scalable and Efficient Object Detection.” ArXiv abs/1911.09070 (2019): n. pag. [3] Bu, Xingyuan et al. “Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019.” ArXiv abs/1910.12044 (2019): n. pag.