2.3 negative sample

[zzzzzz]

I have 1 question and hope to hear from you:
In section, 2.3 ''Each negative key t_ is the pooled feature vector of a view from a different image.''
Why not use the other parts of the two views of the same image as negative samples?
This seems more make sense.

[Xinlong Wang]

Please refer to Section 3.3 of the paper for details, i.e., the paragraph

Negative samples.

.
https://arxiv.org/pdf/2011.09157.pdf

[zzzzzz]

Thank you for your reply.
I saw this part.
Have you tried using the other parts of the two views of the same image as negative samples?
This seems more 'hard negative' than sample from a different image.

[Xinlong Wang]

We didn't try that.

[zzzzzz]

OK. Thank you very much.

[Zhihao Gu]

I have 1 question and hope to hear from you:
In section, 2.3 ''Each negative key t_ is the pooled feature vector of a view from a different image.''
Why not use the other parts of the two views of the same image as negative samples?
This seems more make sense.

So the 'pooled feature vector of a view from a different image' means the global average pooled vector of a view from a different image? If so, t_ is equal to the global view of a different image?