Two questions about denoising design, which might effect the performace

[DeclK]

Hi, I love the detrex project, such a great work! I am reading the DINO codes, and I have 2 questions about the denoising design:

1. When making the denoising query, it will pad some zero to make it a batch. But in the calculation, it seems the padded zero will be calculated in attention, because the attention mask does not consider the zero padding. Since the performance of DINO and DN-DETR are great, so it makes me think, how much would this design affect the network. Have you guys tried to consider this masking?
2. When doing contrastive denoising, the negative noise would be large, according to the code, there might be a change that there might be invalid negative boxes, because the w & h could be less than 0, is this also part of the plan?
   

   detrex/projects/dino/modeling/dino.py

   Lines 424 to 433 in 67f703b

   	rand_sign = (
   	torch.randint_like(known_bboxs, low=0, high=2, dtype=torch.float32) * 2.0 - 1.0
   	)
   	rand_part = torch.rand_like(known_bboxs)
   	rand_part[negative_idx] += 1.0
   	rand_part *= rand_sign
   	known_bbox_ = known_bbox_ + torch.mul(rand_part, diff).cuda() * box_noise_scale
   	known_bbox_ = known_bbox_.clamp(min=0.0, max=1.0)
   	known_bbox_expand[:, :2] = (known_bbox_[:, :2] + known_bbox_[:, 2:]) / 2
   	known_bbox_expand[:, 2:] = known_bbox_[:, 2:] - known_bbox_[:, :2]