Question about unsup loss.

[heiyuxiaokai]

Here, teacher model and student model respectively adopt different data augment methods. And the strong one uses random crop, which will cause the change in object locations. I'm confused how get_distill_loss works while dense feature maps are not corresponding. https://github.com/Megvii-BaseDetection/DenseTeacher/blob/ca5c29d04674fdb68c389839a2f8d9ec637ad4c9/coco-p10/runner.py#L242 https://github.com/Megvii-BaseDetection/DenseTeacher/blob/ca5c29d04674fdb68c389839a2f8d9ec637ad4c9/coco-p10/runner.py#L244 https://github.com/Megvii-BaseDetection/DenseTeacher/blob/ca5c29d04674fdb68c389839a2f8d9ec637ad4c9/coco-p10/runner.py#L321

[ZRandomize]

seem like your misunderstood the random crop. This augmentation replace a random patch of the image with pure noise, rather than replace the whole image with its patch.

[heiyuxiaokai]

seem like your misunderstood the random crop. This augmentation replace a random patch of the image with pure noise, rather than replace the whole image with its patch.

Therefore, the output images of weak strong augmentation own the same object. I understand, and thanks.

[heiyuxiaokai]

Sorry to trouble you again. RandomFlip in WeakAug also cause the above situation. https://github.com/Megvii-BaseDetection/DenseTeacher/blob/ca5c29d04674fdb68c389839a2f8d9ec637ad4c9/coco-p10/augmentations.py#L64

[ZRandomize]

In this code base, student model use StrongAug + Weak Aug while teacher use Weak Aug. Thus the geometric correspondence was retained. see here

[heiyuxiaokai]

In this code base, student model use StrongAug + Weak Aug while teacher use Weak Aug. Thus the geometric correspondence was retained. see here

I see.