New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fogy_cityscape dataset convert error:The total number of index is not correct for adaptive object detection #119
Comments
I know this is an object with empty labels removed, but removing the empty labels in the test will affect the final accuracy |
mAP50 is calculated only when the IOU exceeds 0.5. |
Thanks to the authors for open-source work,again。 I listed my results hoping to be helpful to other students who have the same problem dataset:Cityscapes to Foggy Cityscapes FOR 500 AP for bus = 0.4898 FOR 492 |
By the way,migration between similar domains always is a difficult problem for domain adaptive object detection。 |
Thanks for your question and results. |
In my opinion, transfer between similar domains is much easier. The real problem is that Cityscapes to Foggy Cityscapes is an ill-defined task since there exists a single-to-single map between the images in the target domain and the source domain, which is not likely encountered in practical applications. (If you really encounter such occasions, you can use a simple solution like CycleGAN.) Since previous work has used this task, we also support this task. |
Thank you very much. It was a great harvest |
Is the two supported method cycleGAN and Decouple Adaptation independent with each other, by the way, where is the adversarial process in cycleGAN, does it works like HTCN? @JunguangJiang @microhhh @zyfone Many thanks |
cycleGAN is a kind of method which is used to augment dataset。 clipart or cityscape,for example 。 Decouple Adaptation is a domain adaptive obejct detection method which decouple domain procedure to enhance Transferability and Discriminability 。 Therefore,they are independent of each other。you also can use cycleGAN to get new target-like dataset in your train-set. It works like HTCN. Beause of the need of fair comparison. |
hello thanks for developing this lib
i get voc style dataset of cityscape/fogy_cityscape in prepare_cityscapes_to_voc.py
but i find index of ImageSets/Main/test.txt which only have 493 indexs ,but there are 500 in paper
The text was updated successfully, but these errors were encountered: