面向细粒度时尚图像检索的多头持续学习框架：基于对比学习与指数移动平均蒸馏
A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
AI总结：
本文提出MCL-FIR框架，通过多头设计和对比学习结合EMA蒸馏，实现细粒度时尚图像检索的持续学习，实验表明其在效率与精度上优于现有方法。
摘要：
大多数细粒度时尚图像检索（FIR）方法假设静态环境，当新属性出现时需要完整重新训练，这在动态场景中成本高且不现实。尽管预训练模型支持零样本推理，但缺乏监督时精度下降，且无先驱工作探索细粒度FIR的类增量学习（CIL）。我们提出一种面向细粒度时尚图像检索的多头持续学习框架，结合对比学习和指数移动平均（EMA）蒸馏（MCL-FIR）。MCL-FIR采用多头设计以适应增量演变的类别，将三元组输入改造成双元组以InfoNCE进行更简单有效的训练，并利用EMA蒸馏实现高效的知识转移。在四个数据集上的实验表明，除可扩展性外，MCL-FIR在效率和精度之间实现了良好平衡。在相似训练成本下，其显著优于CIL基线，与静态方法相比，其性能相当但训练成本仅为约30%。源代码可在https://github.com/Dr-LingXiao/MCL-FIR公开获取。
英文摘要：
Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot inference, their accuracy drops without supervision, and no prior work explores class-incremental learning (CIL) for fine-grained FIR. We propose a multihead continual learning framework for fine-grained fashion image retrieval with contrastive learning and exponential moving average (EMA) distillation (MCL-FIR). MCL-FIR adopts a multi-head design to accommodate evolving classes across increments, reformulates triplet inputs into doublets with InfoNCE for simpler and more effective training, and employs EMA distillation for efficient knowledge transfer. Experiments across four datasets demonstrate that, beyond its scalability, MCL-FIR achieves a strong balance between efficiency and accuracy. It significantly outperforms CIL baselines under similar training cost, and compared with static methods, it delivers comparable performance while using only about 30% of the training cost. The source code is publicly available in https://github.com/Dr-LingXiao/MCL-FIR.
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。
