Rigidity Preserving Image Transformations and Equivariance in Perspective

用于不变自监督学习的软等价性正则化

Soft Equivariance Regularization for Invariant Self-Supervised Learning

本文提出软等价性正则化，通过解耦不变性和等价性强制的层，提升自监督学习在ImageNet-1k和ImageNet-C/P等任务中的性能。

增强图像恢复Transformer的自适应平移等变性

Enhancing Image Restoration Transformer via Adaptive Translation Equivariance

针对图像恢复Transformer中注意力破坏平移等变性的问题，提出滑动索引与组件堆叠策略，并开发自适应滑动索引机制构建TEAFormer，在多种恢复任务上提升了有效性、收敛性和泛化性。

通过预测未来表示学习OCT中退行性疾病进展的时间等变性

Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations

提出时间等变对比学习（TC）方法，通过预测未来表示并保持对无关变换的不变性，有效捕捉纵向OCT中退行性疾病进展，在AMD进展预测上优于现有方法。

Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks

Convolutional neural networks (CNN) are now being widely used for classifying and detecting pulmonary abnormalities in chest radiographs. Two complementary generalization properties of CNNs, translation invariance and equivariance, are particularly useful in detecting manifested abnormalities associated with pulmonary disease, regardless of their spatial locations within the image. However, these properties also come with the loss of exact spatial information and global relative positions of abnormalities detected in local regions. Global relative positions of such abnormalities may help disti…

基于变换图像重建的自监督学习用于等变-相干特征表示

Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

本文提出一种基于变换图像重建的自监督学习方法，通过学习等变-相干特征表示，提升模型在等变任务中的表现，同时保持不变特征的性能。

结构保持扩散模型

Structure Preserving Diffusion Models

本文提出结构保持扩散模型的新框架，通过补充必要条件并设计结构保持桥接模型，在对称分布学习、等变图像降噪和风格迁移等任务中验证了其有效性与实用性。