Rethinking ImageNet Pre-Training

ICCV, pp. 4917-4926, 2019.

Cited by: 185|Bibtex|Views222|Links
EI

Abstract:

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization. The results are no worse than their ImageNet pre-training counterparts even when using the hyper-parameters of the baseline system (Mask R-CNN) that were optimized for fine-tuning pre-...More

Code:

Data:

Your rating :
0

 

Tags
Comments