Figure 1 Additional analysis

We answer each question below. Our strong empirical results backs our design choice. As noted in the main paper (see section 3.3 Framework Design), we learn target-to-source alignment Thus, the '+trad' must be replaced with /check. The clear improvement demonstrates its efficacy. The followings are the results: [Ours 32.0 / ADVENT 29.1 / Adaptseg R1,R4: end-to-end training The end-to-end training causes the model to diverge.