Review for NeurIPS paper: Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

Weaknesses: 1. Figure 2 is very confusing to me. Figure (2a) seems to train an individual classifier for each domain. Figure (2b) seems also to train an individual classifier for each domain but also require the agreement across all classifiers for all samples. My question is what is the difference between Figure 2b and the method only train one classifier for all domains? It seems to me that training several classifiers and alignment them with a loss is same as only training one classifier. Furthermore, I agree that alignment classifiers can align features across domains as well, but the previous methods also use some distance loss or adversarial learning to align classifiers or features, which will reach a similar performance.