The recent end-to-end co-saliency models have good performance, however, they cannot express the semantic consistency among a group of images well and usually require many co-saliency labels. To this end, a two-stream encoder generative adversarial network (TSE-GAN) with progressive training is proposed in this paper. In the pre-training stage, the salient object detection generative adversarial networks (SOD-GAN) and classification network (CN) are separately trained by the salient object detection (SOD) datasets and co-saliency datasets with only category labels to learn the intra-saliency and preliminary inter-saliency cues and alleviate the problem of insufficient co-saliency labels. In the second training stage, the backbone of TSE-GAN is inherited from the trained SOD-GAN, the encoder of trained SOD-GAN (SOD-Encoder) is used to extract intra-saliency features, the group-wise semantic encoder (GS-Encoder) is constructed by the multi-level group-wise category features extracted from CN for extracting inter-saliency features with better semantic consistency, the TSE-GAN constructed by incorporating the GS-Encoder into SOD-GAN is trained on co-saliency datasets for co-saliency detection. The comprehensive comparisons with 13 state-of-the-art methods demonstrate the effectiveness of proposed method.

中文翻译：

---

两流编码器GAN，具有逐步训练的共显着性检测

最近的端到端共同显着性模型具有良好的性能，但是，它们不能很好地表达一组图像之间的语义一致性，并且通常需要许多共同显着性标签。为此，本文提出了一种具有渐进训练的两流编码器生成对抗网络（TSE-GAN）。在预训练阶段，显着目标检测生成对抗网络（SOD-GAN）和分类网络（CN）分别由显着目标检测（SOD）数据集和共显着性数据集（仅带有类别标签）进行训练，以学习内部-显着性和初步的显着性暗示，并缓解了共同显着性标签不足的问题。在第二个训练阶段，TSE-GAN的骨干是从训练有素的SOD-GAN继承而来的，使用训练有素的SOD-GAN编码器（SOD-Encoder）提取内部显着特征，通过从CN提取的多层次分组类别特征构造分组语义编码器（GS-Encoder），以提取内部-显着性特征具有更好的语义一致性，通过将GS-Encoder合并到SOD-GAN中构建的TSE-GAN在共同显着性数据集上进行训练，以进行共同显着性检测。与13种最先进方法的全面比较证明了所提出方法的有效性。通过将GS编码器合并到SOD-GAN中构建的TSE-GAN在共同显着性数据集上进行了训练，以进行共同显着性检测。与13种最先进方法的全面比较证明了所提出方法的有效性。通过将GS编码器合并到SOD-GAN中构建的TSE-GAN在共同显着性数据集上进行了训练，以进行共同显着性检测。与13种最先进方法的全面比较证明了所提出方法的有效性。