Learning Data Augmentation Strategies for Object Detection

26 Jun 2019Barret ZophEkin D. CubukGolnaz GhiasiTsung-Yi LinJonathon ShlensQuoc V. Le

Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev NAS-FPN (AmoebaNet-D, learned aug) box AP 50.7 # 10
APS 34.2 # 9
APM 55.5 # 7
APL 64.5 # 8
Object Detection PASCAL VOC 2007 Faster R-CNN (ResNet-101, learned aug) MAP 78.7% # 11

Methods used in the Paper