Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.

翻译：图像间关联建模对于共显著目标检测至关重要。尽管现有方法已取得令人满意的性能，但在充分的图像间关联建模方面仍存在局限性。这是因为大多数方法侧重于在启发式计算的原始图像间关联指导下进行图像特征优化。这些方法直接依赖原始关联，而原始关联在复杂场景中并不可靠，且其图像特征优化方法对图像间关联建模不够显式。为缓解这些局限性，本文提出一种深度关联学习策略，通过在原始关联上部署深度网络，将其显式转换为深度关联特征。具体而言，我们首先创建超关联以收集密集的像素对原始关联，随后在其上部署深度聚合网络。为此我们设计了渐进式关联生成模块，并额外增强了超关联计算。更重要的是，我们提出对应关系诱导的关联压缩模块，通过引入语义对应估计这一前置任务来压缩超关联，从而降低计算负担并消除噪声。同时设计了面向目标的循环一致性损失函数以获取高质量的对应关系估计。在三个基准数据集上的实验结果表明，本方法在不同训练设置下均具有显著的有效性。