Missing very important baseline about openlongtailrecognition-oltr

[zhmiao]

@twangnh Thanks for asking. Yes, we have tried upsampling methods although we did not report it due to space limit. We also incorporated upsampling (class-aware samping) into our code. You are very welcome to single out this module and test it out.

[tonysy]

I think another important baseline is just use the weight normalization or cosine normalization without memory mechanism.

[liuziwei7]

All the comparison methods in Table 3 of the main paper (https://arxiv.org/pdf/1904.05160.pdf) are equipped with class-aware/balanced sampling, as elaborated in Section 4 "Competing Methods". You are more than welcome to try other variants of ablation study.