Question about the mask decoder: why discard the first mask in multimask?

```
# Select the correct mask or masks for output
if multimask_output:
masks = masks[:, 1:, :, :]
iou_pred = iou_pred[:, 1:]
elif self.dynamic_multimask_via_stability and not self.training:
masks, iou_pred = self._dynamic_multimask_via_stability(masks, iou_pred)
else:
masks = masks[:, 0:1, :, :]
iou_pred = iou_pred[:, 0:1]

if multimask_output and self.use_multimask_token_for_obj_ptr:
sam_tokens_out = mask_tokens_out[:, 1:] # [b, 3, c] shape
else:
# Take the mask output token. Here we *always* use the token for single mask output.
# At test time, even if we track after 1-click (and using multimask_output=True),
# we still take the single mask token here. The rationale is that we always track
# after multiple clicks during training, so the past tokens seen during training
# are always the single mask token (and we'll let it be the object-memory token).
sam_tokens_out = mask_tokens_out[:, 0:1] # [b, 1, c] shape

```
[link to code](https://github.com/facebookresearch/segment-anything-2/blob/7e1596c0b6462eb1d1ba7e1492430fed95023598/sam2/modeling/sam/mask_decoder.py#L146C9-L146C29)

I wonder why just discard the first mask in masks(multiple mask)?
Is it because the first mask only used for single mask output in training so it doesn't apply to multimask output in inference?
I don't think it's in the paper. Maybe I missed it, does anyone has an answer? Thanks.