Rethinking ImageNet Pre-training

CoRR, Volume abs/1811.08883, 2018.

Cited by: 230|Bibtex|Views239
EI
Other Links: dblp.uni-trier.de|arxiv.org

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:

Full Text
Your rating :
0

 

Tags
Comments