search

xinw1012 / cycle-confusion

Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".
https://xinw.ai/cyc-conf
Apache License 2.0
74 stars 9 forks source link

Code for a conventional unsupervised domain adaptation in an image. #3

Open natureyoo opened 2 years ago

natureyoo commented 2 years ago

Thank you for your interesting work. It was very impressive to improve the robustness to domain shift through self-supervision.

In particular, I'm interested in conventional UDA settings (e.g. cityscapes -> foggy cityscapes, Sim10k -> cityscapes) that you applied rotation operation as a self-supervision task. Could you release the code for this, as well?

natureyoo commented 2 years ago

Hi, I implemented the code for UDA settings and it works well. Thank you. But, I found only ResNet50 config and codes although the experiment results were on VGG16 and Res101 backbones. Could you release vgg16 and res101 config files? I tried training with vgg16 backbone, but it doesn't work well. Thank you

ichuniq commented 2 years ago

Thanks @xinw1012 for sharing this work and @natureyoo for asking this question

I also implemented the UDA settings as mentioned in the paper. However, my results(mAP50) when using Res101 backbone didn't work that well.

For CityScape to Foggy, my results for (src-only, rotation, oracle) was (25.89, 35.38, 49.79), while the results in the paper were (25.6, 41.5, 48.6) I have tried to recreate it according to the description alongside the training config mentioned in the implementation details.

@natureyoo, could you share the numbers you got using Res50 and VGG or even Res101? Looking forward to some help and the code release for the UDA settings, thanks!

natureyoo commented 2 years ago

I'm sorry for the late reply. I've got mAP@50 (24.45, 35.45) for (src-only, rotation) using Res50 and (27.7, 34.94) with Res101. The result for Res101 would not be the optimal one because I didn't fine-tune it at all, but there was no performance gain than Res50.