在解耦潜在图像表示中学习群作用
Learning Group Actions In Disentangled Latent Image Representations
AI总结：
本文提出了一种端到端框架，自动学习潜在图像表示中的群作用，无需人工干预，通过动态划分潜在表示实现变换敏感和不变成分的解耦。
摘要：
对潜在表示中的群作用建模能够实现高维图像数据的可控变换。先前应用群论先验或建模变换的工作通常在高维数据空间中操作，其中群作用在整个输入上均匀应用，使得难以解耦在变换下变化的子空间。虽然潜在空间方法提供了更大的灵活性，但它们仍然需要手动将潜在变量划分为等变和不变的子空间，限制了在表示空间中稳健地学习和操作群作用的能力。为了解决这个问题，我们引入了一个新颖的端到端框架，首次在潜在图像流形上学习群作用，自动发现与变换相关的结构，而无需人工干预。我们的方法使用可学习的二进制掩码与直通估计来动态地将潜在表示划分为对变换敏感和不变的组成部分。我们将此建模在一个统一的优化框架内，联合学习潜在解耦和群变换映射。该框架可以无缝集成到任何标准的编码器-解码器架构中。我们在五个2D/3D图像数据集中验证了我们的方法，证明了其能够自动学习不同数据中的解耦潜在因素以进行群作用，同时下游分类任务确认了所学表示的有效性。我们的代码在https://github.com/farhanaswarnali/Learning-Group-Actions-In-Disentangled-Latent-Image-Representations 上公开可用。
英文摘要：
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data space, where group actions apply uniformly across the entire input, making it difficult to disentangle the subspace that varies under transformations. While latent-space methods offer greater flexibility, they still require manual partitioning of latent variables into equivariant and invariant subspaces, limiting the ability to robustly learn and operate group actions within the representation space. To address this, we introduce a novel end-to-end framework that for the first time learns group actions on latent image manifolds, automatically discovering transformation-relevant structures without manual intervention. Our method uses learnable binary masks with straight-through estimation to dynamically partition latent representations into transformation-sensitive and invariant components. We formulate this within a unified optimization framework that jointly learns latent disentanglement and group transformation mappings. The framework can be seamlessly integrated with any standard encoder-decoder architecture. We validate our approach on five 2D/3D image datasets, demonstrating its ability to automatically learn disentangled latent factors for group actions in diverse data, while downstream classification tasks confirm the effectiveness of the learned representations. Our code is publicly available at https://github.com/farhanaswarnali/Learning-Group-Actions-In-Disentangled-Latent-Image-Representations .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
