SimO Loss：面向细粒度监督对比学习的无锚点对比损失
SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning
AI总结：
本研究提出一种基于SimO损失的无锚点对比学习方法，通过半度量损失同时优化相似/不相似样本的嵌入距离与正交性，在CIFAR-10上验证其能形成结构良好的类别邻域，为表征几何特性的应用提供新思路。
摘要：
我们提出了一种全新的无锚点对比学习（AFCL）方法，该方法采用我们提出的相似度-正交性（SimO）损失。我们的方法最小化一个半度量判别损失函数，该函数同时优化两个核心目标：缩小相似输入嵌入之间的距离并提升其正交性，同时增大不相似输入的这两项指标，从而实现更细粒度的对比学习。由SimO损失驱动的AFCL方法会在嵌入空间中形成纤维丛拓扑结构，构建出类别专属、内部凝聚且相互正交的邻域。我们在CIFAR-10数据集上验证了该方法的有效性，并通过可视化展示了SimO损失对嵌入空间的影响。实验结果显示，该方法形成了清晰、正交的类别邻域，证明其能够构建结构良好的嵌入，平衡类别分离度与类内变异性。这项工作为理解和利用学习表征的几何特性以应用于各类机器学习任务开辟了新路径。
英文摘要：
We introduce a novel anchor-free contrastive learning (AFCL) method leveraging our proposed Similarity-Orthogonality (SimO) loss. Our approach minimizes a semi-metric discriminative loss function that simultaneously optimizes two key objectives: reducing the distance and orthogonality between embeddings of similar inputs while maximizing these metrics for dissimilar inputs, facilitating more fine-grained contrastive learning. The AFCL method, powered by SimO loss, creates a fiber bundle topological structure in the embedding space, forming class-specific, internally cohesive yet orthogonal neighborhoods. We validate the efficacy of our method on the CIFAR-10 dataset, providing visualizations that demonstrate the impact of SimO loss on the embedding space. Our results illustrate the formation of distinct, orthogonal class neighborhoods, showcasing the method's ability to create well-structured embeddings that balance class separation with intra-class variability. This work opens new avenues for understanding and leveraging the geometric properties of learned representations in various machine learning tasks.
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。
