Detecting and segmenting salient objects from given image scenes has received great attention in recent years. A fundamental challenge in training the existing deep saliency detection models is the requirement of large amounts of annotated data. While gathering large quantities of training data becomes cheap and easy, annotating the data is an expensive process in terms of time, labor and human expertise. To address this problem, this paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only, thus dramatically alleviating human labor in training models. To this end, we name this new task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario. Essentially, APL is derived from the self-paced learning (SPL) regime but it infers the robust learning pace through the data-driven adversarial learning mechanism rather than the heuristic design of the learning regularizer. Comprehensive experiments on four widely-used benchmark datasets have demonstrated that the proposed approach can effectively approach to the existing supervised deep salient object detection models with only 1k human-annotated training images.

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.

This paper received reviews from 3 expert reviewers. The reviewers appreciated the interesting task (few cost saliency detection) and the use of self-paced learning combined with generative adversarial learning. After considering the authors' response, the reviewers refined their positions on the paper. R2's comments regarding semi-supervised learning remain valid. The authors would be encouraged to refine the presentation of this and use of terms.

Detecting and segmenting salient objects from given image scenes has received great attention in recent years. A fundamental challenge in training the existing deep saliency detection models is the requirement of large amounts of annotated data. While gathering large quantities of training data becomes cheap and easy, annotating the data is an expensive process in terms of time, labor and human expertise. To address this problem, this paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only, thus dramatically alleviating human labor in training models. To this end, we name this new task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.