Closed liyangliu closed 4 years ago
Dear Liyang, The ADDITIONAL_LINEAR_CLS_LOSS is a cross-entropy loss computed for an additional linear classifier, trained together with the distance-based classifier. You can see the layer in fpn/symbols/resnet_v1_101_fpn_dcn_rcnn_oneshot_v3.py, line 1167. It is used during the training on base classes, and discarded for the few-shot experiments.
Hi, @jshtok
I find in the paper that there are only cross entropy loss and embed loss for few shot detection (as for the classification branch) but in your code there is another loss called ADDITIONAL_LINEAR_CLS_LOSS. https://github.com/jshtok/RepMet/blob/d5b13e01940bbb7ed59dd1ff073e03c0808f76c0/fpn/symbols/resnet_v1_101_fpn_dcn_rcnn_oneshot_v3.py#L1167-L1168 https://github.com/jshtok/RepMet/blob/d5b13e01940bbb7ed59dd1ff073e03c0808f76c0/fpn/symbols/resnet_v1_101_fpn_dcn_rcnn_oneshot_v3.py#L1205-L1206 What is this loss used for ? Thanks.