Few questions for reproducing the results on Watercolor

VisionLearningGroup / DA_Detection

Implementation of "Strong-Weak Distribution Alignment for Adaptive Object Detection"

http://cs-people.bu.edu/keisaito/research/CVPR2019.html

MIT License

347 stars 80 forks source link

Few questions for reproducing the results on Watercolor #18

Open BOBrown opened 5 years ago

BOBrown commented 5 years ago

Hi, I'm trying to reproduce your work for VOC->Watercoloc dataset but have several issues. Q1: Watercolor dataset only has 7 classes (including the background), but VOC has 21 classes. Should I use a 7-class-VOC dataset as the source domain during the training process? Q2: Could I finetune from the pretrained model that is trained on 21-class-VOC dataset when I uses the 7-class-VOC dataset as the source domain?

shixiaoyangaaa commented 4 years ago

A1: Only 'bicycle', 'bird', 'car', 'cat', 'dog', 'person'. You can see "pascal_voc_water.py".

Tomlk commented 4 years ago

same question！ when I need watercolor（7）->clipart（21） how to test ？ Please！