通过混合内容-风格调制实现可泛化的共显著目标检测
Generalizable Co-Salient Object Detection via Mixed Content-Style Modulation
该文将CLIP语义嵌入与交叉注意力结合提取域不变场景结构先验，并通过合成特征统计量（均值/方差）做源域风格增强，为视觉分割任务在未见域上的泛化提供了一套可复用的内容-风格调制思路。
原文依据 the MSM addresses the uncertainty associated with domain shifts by synthesizing feature statistics, such as mean and standard deviation, during training to simulate new stylistic characteristics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出了一种通过混合内容-风格调制实现的可泛化共显著目标检测框架CoMCS，以增强模型对未见域的鲁棒性。CoMCS由混合内容调制器（MCM）、混合风格调制器（MSM）和协作语义对比模块（SCM）组成，能够有效提取场景结构先验并增强源域风格，从而弥合源域与未见域之间的域差距。具体而言，CoMCS首先利用CLIP模型提取整个场景中与语义类别相关的概念知识，得到域不变的多类语义嵌入。随后，MCM通过交叉注意力机制建模共显著目标原型与多类语义嵌入之间的语义关系，有效捕获域不变的场景结构先验，有助于减少未见域中的场景分布偏移。同时，为缓解测试过程中遇到的域扰动，MSM通过在训练期间合成特征统计量（如均值和标准差）来模拟新的风格特征，以应对域偏移带来的不确定性，从而在源域内实现数据增强。最后，为减少来自未见域的测试数据中共显著目标表示的模糊性，SCM采用均匀损失函数确保学习到的原型在超球面空间中均匀分布，进一步增强框架的域泛化能力。此外，为进一步验证CoMCS对未见域的泛化能力，我们构建了一个未见域基准数据集（UND），该数据集从CoCA、CoSOD3k、CoSal2015中选取了多种具有未见类别的图像组。在四个基准数据集上的广泛评估表明，我们的CoMCS相较于多种最优方法取得了有利的性能。
英文原文摘要 2003 字符
This paper presents a generalizable CoSOD framework via mixed content-style modulation, termed CoMCS, to enhance the robustness of the model to unseen domains. The CoMCS, consisting of a mixed content modulator (MCM), a mixed style modulator (MSM), and a collaborative semantic contrast module (SCM), effectively extracts scene structure priors as well as augments the source domain styles to bridge the domain gap between the source and the unseen domains. Specifically, the CoMCS first utilizes the CLIP model to extract conceptual knowledge associated with the semantic classes in the whole scene, resulting in multi-class semantic embeddings that are domain-invariant. Subsequently, the MCM models the semantic relationships between the prototypes of co-salient objects and the multi-class semantic embeddings through the cross-attention mechanism, effectively capturing domain-invariant scene structure priors that aid in reducing scene distribution shift in unseen domains. Meanwhile, to alleviate domain perturbations encountered during testing, the MSM addresses the uncertainty associated with domain shifts by synthesizing feature statistics, such as mean and standard deviation, during training to simulate new stylistic characteristics, thus achieving data augmentation within the source domain. Finally, to reduce the ambiguity of the co-salient object representations within test data from unseen domains, the SCM employs a uniform loss function to ensure that the learned prototypes are uniformly distributed within the hyperspherical space, further enhancing the domain generalization capabilities of the framework. Besides, to further verify the generalization ability of the CoMCS to unseen domains, we construct an unseen-domain benchmark dataset (UND) that selects a variety of image groups with unseen classes from CoCA, CoSOD3k, CoSal2015. Extensive evaluations on the four benchmark datasets demonstrate favorable performance of our CoMCS to a variety of state-of-the-art methods.