Abstract
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 this https URL.
Abstract (translated)
大多数细粒度时尚图像检索（FIR）方法假设静态设置，当新属性出现时需要完全重新训练，这在动态场景中成本高昂且不切实际。尽管预训练模型支持零样本推理，但在无监督情况下其准确率会下降，且尚无先前工作探索用于细粒度FIR的类增量学习（CIL）。我们提出了一种结合对比学习与指数移动平均（EMA）蒸馏的多头部持续学习框架（MCL-FIR），用于细粒度时尚图像检索。MCL-FIR采用多头部设计以适应增量过程中不断演变的类别，将三元组输入重构为双元组并采用InfoNCE损失以实现更简洁有效的训练，同时利用EMA蒸馏实现高效的知识迁移。在四个数据集上的实验表明，除可扩展性外，MCL-FIR在效率与准确率间取得了强平衡：在相似训练成本下显著优于CIL基线方法；与静态方法相比，其性能相当但训练成本仅约30%。源代码已公开于此链接。
URL
https://arxiv.org/abs/2603.20648
