Learning Data Augmentation Strategies for Object Detection

Barret Zoph; Ekin D. Cubuk; Golnaz Ghiasi; Tsung-Yi Lin; Jonathon Shlens; Quoc V. Le

ECCV 2020poster752 citations

Learning Data Augmentation Strategies for Object Detection

Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, Quoc V. Le

Abstract

Much research on object detection focuses on building better model architectures and detection algorithms. Changing the model architecture, however, comes at the cost of adding more complexity to inference, making models slower. Data augmentation, on the other hand, doesn't add any inference complexity, but is insufficiently studied in object detection for two reasons. First it is more difficult to design plausible augmentation strategies for object detection than for classification, because one must handle the complexity of bounding boxes if geometric transformations are applied. Secondly, data augmentation attracts less research attention perhaps because it is believed to add less value and to transfer poorly compared to advances in network architectures.

BibTeX

@inproceedings{eccv2020_learningdataaugm,
  title = {Learning Data Augmentation Strategies for Object Detection},
  author = {Barret Zoph and Ekin D. Cubuk and Golnaz Ghiasi and Tsung-Yi Lin and Jonathon Shlens and Quoc V. Le},
  booktitle = {ECCV 2020},
  year = {2020}
}