Importance of w,w/o FPN in DeFRCN

[er-muyue]

Importance of w,w/o FPN in DeFRCN

[MartinYYYYan]

@buncybunny I have tried to add 3 more Affine layers for each channel of RPN. When I FT the model, I have frozen the backbone(5-levels) and unfrozen the FPN, RPN, ROI-HEAD. The performance is similar to RES5ROI model. (1% difference in Base Class and Novel class mAP50).

[ssyze]

@MartinYYYYan I'm sorry that could you share your FPN config file with me? I also add some more Affine layers for the FPN model, but my performance is lower than the RES5ROI model by about 2-5% in any shot. I'm quite confused about this. Thx a lot!

[er-muyue]

Hi @buncybunny, I think you have the similary question with this issue. Actually, FPN is not a necessary module for verifying the performance of DeFRCN. We directly adopted Res5ROIHeads in our paper. If there is enough time next, I will experiment on FPN and provide the experimental results in this repo.