论文标题
迈向稳定的共同检测和对象共段
Towards Stable Co-saliency Detection and Object Co-segmentation
论文作者
论文摘要
在本文中，我们提出了一个新型模型，用于同时稳定的共同检测（COSOD）和对象共裂（Coseg）。为了准确地检测共同水平（分割），核心问题是对图像组之间的图像间关系进行良好的模型。一些方法设计了复杂的模块，例如复发性神经网络（RNN），以解决此问题。但是，对订单敏感的问题是RNN的主要缺点，这严重影响了拟议的COSOD（COSEG）模型的稳定性。在本文中，受到基于RNN的模型的启发，我们首先提出了一个多路稳定的复发单元（MSRU），其中包含虚拟订单机制（DOM）和复发单元（RU）。我们提出的MSRU不仅有助于COSOD（COSEG）模型捕获稳健的图像间关系，还可以降低订单敏感性，从而导致更稳定的推理和训练过程。 {此外，我们设计了一个跨级对比损失（COCL），可以通过关闭从不同输入顺序产生的嵌入功能来进一步解决订单敏感问题。}我们在五个广泛使用的COCA，COCA，COSOD3K，COSAL2015，ICOSEG和MSRC，ICOSE和ICOSE（iCOSE）（ICTASE）（ICTASE）（ICTOSE，ICTAS）（ICTOS，ICTOSE）上验证了我们的模型（COCA，COSOD3K，COSAL2015，COSAL2015，ICOSEG和MSRC）与最新方法（SOTA）方法相比，共同分割的性能证明了所提出的方法的优势。
In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG). To detect co-saliency (segmentation) accurately, the core problem is to well model inter-image relations between an image group. Some methods design sophisticated modules, such as recurrent neural network (RNN), to address this problem. However, order-sensitive problem is the major drawback of RNN, which heavily affects the stability of proposed CoSOD (CoSEG) model. In this paper, inspired by RNN-based model, we first propose a multi-path stable recurrent unit (MSRU), containing dummy orders mechanisms (DOM) and recurrent unit (RU). Our proposed MSRU not only helps CoSOD (CoSEG) model captures robust inter-image relations, but also reduces order-sensitivity, resulting in a more stable inference and training process. { Moreover, we design a cross-order contrastive loss (COCL) that can further address order-sensitive problem by pulling close the feature embedding generated from different input orders.} We validate our model on five widely used CoSOD datasets (CoCA, CoSOD3k, Cosal2015, iCoseg and MSRC), and three widely used datasets (Internet, iCoseg and PASCAL-VOC) for object co-segmentation, the performance demonstrates the superiority of the proposed approach as compared to the state-of-the-art (SOTA) methods.
