In this paper, we present a novel end-to-end group collaborative learning network, termed GCoNet+, which can effectively and efficiently (250 fps) identify co-salient objects in natural scenes. The proposed GCoNet+ achieves the new state-of-the-art performance for co-salient object detection (CoSOD) through mining consensus representations based on the following two essential criteria: 1) intra-group compactness to better formulate the consistency among co-salient objects by capturing their inherent shared attributes using our novel group affinity module (GAM); 2) inter-group separability to effectively suppress the influence of noisy objects on the output by introducing our new group collaborating module (GCM) conditioning on the inconsistent consensus. To further improve the accuracy, we design a series of simple yet effective components as follows: i) a recurrent auxiliary classification module (RACM) promoting model learning at the semantic level; ii) a confidence enhancement module (CEM) assisting the model in improving the quality of the final predictions; and iii) a group-based symmetric triplet (GST) loss guiding the model to learn more discriminative features. Extensive experiments on three challenging benchmarks, i.e., CoCA, CoSOD3k, and CoSal2015, demonstrate that our GCoNet+ outperforms the existing 12 cutting-edge models. Code has been released at https://github.com/ZhengPeng7/GCoNet_plus.

翻译：在本文中，我们提出了一种新颖的端到端组协同学习网络，命名为GCoNet+，能够有效且高效（250帧/秒）地识别自然场景中的共显著性目标。所提出的GCoNet+通过挖掘共识表示，基于以下两个关键准则实现了共显著性目标检测（CoSOD）的最新性能：1）组内紧凑性，通过我们新颖的组亲和模块（GAM）捕获共显著性目标之间固有的共享属性，从而更好地表述它们之间的一致性；2）组间可分离性，通过引入依赖于非一致共识的新组协作模块（GCM），有效抑制噪声目标对输出的影响。为进一步提升准确性，我们设计了一系列简单而有效的组件，包括：i）循环辅助分类模块（RACM），促进模型在语义层面学习；ii）置信度增强模块（CEM），辅助模型提升最终预测质量；以及iii）基于组的对称三元组（GST）损失，引导模型学习更具判别力的特征。在三个具有挑战性的基准数据集（即CoCA、CoSOD3k和CoSal2015）上进行的大量实验表明，我们的GCoNet+优于现有的12种前沿模型。代码已开源至https://github.com/ZhengPeng7/GCoNet_plus。