liuzhuang13 / DenseNet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
BSD 3-Clause "New" or "Revised" License
4.73k stars 1.07k forks source link

DenseNet on Pascal VOC #47

Closed blateyang closed 5 years ago

blateyang commented 6 years ago

Hi, I think DenseNet is a promising model and I try to take it as the backbone of Faster R-CNN in object detection. I chose DenseNet169 pretrained on ImageNet to replace the ResNet50 backbone of Faster R-CNN and used the same hyperparameters configuration as ResNet50 version of Faster R-CNN. However, the training result of DenseNet version is worse than ResNet50 version(roughly 3% lower on VOC2012 test). Can you help me analyse the reason or give me any advice? @liuzhuang13 Many thanks!

liuzhuang13 commented 5 years ago

We didn't tune the configs and architectures on the faster-rcnn framework. Thus we cannot guarantee the current design is good enough for that.

blateyang commented 5 years ago

Anyway, thanks for replying!