改进深度度量学习三要素，显著提升图像检索效果
Three Things to Know about Deep Metric Learning
- 设计可微分的代理损失函数，解决召回率优化难题
- 结合混元正则化与大批次训练，实现高效模型优化
- 基于预训练模型初始化，适合大规模图像检索任务
本文针对开放集图像检索中的监督式深度度量学习，聚焦损失函数、混元正则化和模型初始化三个关键方面。由于召回率@k（recall@k）不可导，直接通过梯度下降优化困难。为此，我们提出一种在大批次上计算的可微分代理损失，近似整个训练集，克服了传统方法的计算瓶颈。该过程通过绕过GPU内存限制得以实现。此外，我们引入一种在成对相似度上操作的高效混元正则化技术，进一步扩展有效批量大小。训练过程还通过在大规模数据集上预训练的视觉编码器进行初始化，显著提升性能。系统性实验表明，这些组件协同作用使大型模型几乎完全解决主流基准测试。
原文摘要 · Abstract (English)
This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval evaluation metric, recall@k, via gradient descent is desirable but challenging due to its non-differentiable nature. To overcome this, we propose a differentiable surrogate loss that is computed on large batches, nearly equivalent to the entire training set. This computationally intensive process is made feasible through an implementation that bypasses the GPU memory limitations. Additionally, we introduce an efficient mixup regularization technique that operates on pairwise scalar similarities, effectively increasing the batch size even further. The training process is further enhanced by initializing the vision encoder using foundational models, which are pre-trained on large-scale datasets. Through a systematic study of these components, we demonstrate that their synergy enables large models to nearly solve popular benchmarks.
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。