用新损失函数让相似样本更近、不同类更正交，提升细粒度特征学习
SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning
- 提出无锚点对比损失SimO，同时优化相似样本距离与正交性
- 在CIFAR-10上实现类内紧凑、类间正交的嵌入结构
- 适合追求高精度表示学习的视觉任务研究者
我们提出一种新型无锚点对比学习（AFCL）方法，基于所提出的相似性-正交性（SimO）损失。该方法最小化一种半度量判别损失函数，同时优化两个关键目标：减少相似输入嵌入间的距离与正交性，增大不相似输入间的距离与正交性，从而促进更细粒度的对比学习。AFCL方法通过SimO损失在嵌入空间中构建纤维丛拓扑结构，形成类特定、内部紧密且彼此正交的邻域。我们在CIFAR-10数据集上验证了该方法的有效性，可视化结果展示了SimO损失对嵌入空间的影响。结果表明，各类别形成了明显分离、相互正交的邻域，展现了方法在平衡类间分离与类内可变性方面的能力。这项工作为理解并利用学习表示的几何特性开辟了新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。