Closed fliman closed 2 years ago
Hi, thanks for your attention. In fact, we did not use LDAM loss in our work. The provided LDAM loss is provided by the RIDE (https://github.com/frank-xwang/RIDE-LongTailRecognition/blob/main/model/loss.py). You may wanna leave a question in the repository of RIDE. Thanks.
If any other questions, happy to discuss them further.
Hi Vanint, I notice that in your LDAM loss implementation the scale is applied on the the adjustment only
which is different from the original LDAM loss
basically equivalent to
could you explained more on this detail? Is the coefficient absorbed somewhere on the logit output?