Why do we skip cases where the student and teacher operate on the same view? If they are operating on different views, why should they produce similar results to calculate the cross-entropy loss?

[jinghere11]

    total_loss = 0
    n_loss_terms = 0
    for iq, q in enumerate(teacher_out):
        for v in range(len(student_out)):
            if v == iq:
                # we skip cases where student and teacher operate on the same view
                continue
            loss = torch.sum(-q * F.log_softmax(student_out[v], dim=-1), dim=-1)
            total_loss += loss.mean()
            n_loss_terms += 1

[fbliman]

I am not an expert, but my intuition is that feeding the same image will lead to a very small loss and hence an insginificat training, so is wasted resources

but thats only a guess