kjwkch

This issue is code implementation, not performance. I think open code is not implemented as described in the paper.

Missing in the code. # modality fusion ``` feat_learner = F.relu(self.leaners[idx](pts_feat)) feat_cat = torch.cat([img_feat, feat_learner], 1) feat_cat = self.fcs1[idx](feat_cat) feat_weight = torch.sigmoid(self.fcs2[idx](feat_cat)) fuse_feat = F.relu(feat_cat * feat_weight) ``` I think...