Rethinking Pre-training and Self-training

11 Jun 2020Barret ZophGolnaz GhiasiTsung-Yi LinYin CuiHanxiao LiuEkin D. CubukQuoc V. Le

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Object Detection COCO minival SpineNet-190 (1280, with Self-training on OpenImages, single-scale) box AP 54.2 # 2
Object Detection COCO test-dev SpineNet-190 (1280, with Self-training on OpenImages, single-scale) box AP 54.3 # 3
Semantic Segmentation PASCAL VOC 2012 test EfficientNet-L2+NAS-FPN (single scale test, with self-training) Mean IoU 90.5% # 1
Semantic Segmentation PASCAL VOC 2012 val EfficientNet-L2+NAS-FPN (single scale test, with self-training) mIoU 90.0% # 1

Methods used in the Paper