aooating

19+1 setting

3

In this setting, can you send me the trained model? Because there is a gap between my results and the original.

the results of task1

13

In Task1, my current class AP50 was 73.0, which was quite different from the results in the paper, and the U-recall was only 4.4. I don't know why. Can you...

about training on VOC dataset and other backbone

1

Is there a config file for training on the VOC dataset? If other backbones are used, such as TResNet-M, do the corresponding model parameters need to be adjusted?

Distribution-preserving calibration

1

The part of selecting samples isn't in the code, is it?

The visualization in Figure 4 is intuitive. The data is radially distributed in the Euclidean space. I wonder if it has been processed in some way or is it the...