Review for NeurIPS paper: Few-Cost Salient Object Detection with Adversarial-Paced Learning

Some related works missing There are some recent related works, such as [Ref. 1 Ref.6]. In [Ref. 1, 2], the authors integrated the self-paced learning into the object co-saliency detection related to the addressed task of this paper. These two are close to the proposed work, and it is better to provide the discussion. In [Ref 5, and Ref. 6], the authors also combine self-paced learning and adversarial learning, and I think these two works are mostly related to the proposed method, and I would like to see the difference between the proposed method and [Ref 5 and 6] Besides, in [3, 23, 27], semi-supervised learning for saliency detection is addressed, but in this paper, there is no detailed discussion between semi-supervised learning [23, 27] and the proposed few-cost setting. The primary difference should be provided.