Closed woxue closed 4 years ago
You can appropriately increase the border of the detected bbox so that it can contain the background area.
More details can be found in https://github.com/YYuanAnyVision/mxnet_mtcnn_face_detection/blob/b56065418b63a971fcf4f8f35d058513b0ce6cbf/main.py#L22
Figure 4. Grad-CAM [32] visualizations in your paper show some of the input images. I notice that you used not only the face map but part of the background, could you please tell me the detail about data processing.When I crop the face with detected bbox, no background will be left. Thx for your great job~