The implementation of instance segmentation. about meta-detr

[ZhangGongjie]

Thanks for your interest. The codes I wrote for few-shot instance segmentation is a mess and are only used for a simple experiment.... Thus I do not have plans to release them.

[hq-deng]

Could your please send me a script for reference? No need to organize and verify. My email is "[email protected]". Thanks.

[ZhangGongjie]

Done.

[nanfangAlan]

@ZhangGongjie Could you please send me the instance segmentation code also? My email is "[email protected]". Thanks

[ZhangGongjie]

@nanfangAlan I have left Nanyang Technological University and thus I no longer have access to the codes. So sorry about that.

You may try to contact [email protected] for the `messy' codes.

Besides, the implementation is actually very simple. It is the exact implementation as the original DETR, except that we designed the pipeline as a meta-learning setup. When the few-shot finetuning is done, we freeze all object-detection-related parameters and the backbone parameters and train an additional instance segmentation head.

Hope the above clarifies. Feel free to contact me for more details.

[nanfangAlan]

@ZhangGongjie Thanks for your reply. I'm checking the seg code in the original DETR. There are two more questions: 1. Which random seed sample can get the highest score and the "Results over a single run" score in your paper? 2. Did the other methods of "Results averaged over multiple random runs" take the same 10 random support sets as yours?