Closed fake-warrior8 closed 1 year ago
Hi, yes, Unicorn is jointly trained on datasets from four tasks and there is only one set of parameters across four tasks. Table 1, 3, 4, 6 use ConvNeXt-Large as the backbone. While we use ConvNeXt-Tiny as the backbone for ablations.
Hi, yes, Unicorn is jointly trained on datasets from four tasks and there is only one set of parameters across four tasks. Table 1, 3, 4, 6 use ConvNeXt-Large as the backbone. While we use ConvNeXt-Tiny as the backbone for ablations.
Thank you for your reply.
Hi, in Sec 4.1, the paper said that Unicorn in four tasks uses the same model parameters, does this mean that the Unicorn model is trained in a multi task manner? Meanwhile, I found that in the ablation study in Sec 4.6, the four results of Unification in the Single task part of Table 7 are different from the results in Tables 1, 3, 4, 6, what is the difference between the Unification setting in Table 7 and those in Table 1,3, 4, 6?