双不平衡持续学习用于现实世界的食物识别
Dual-Imbalance Continual Learning for Real-World Food Recognition
AI总结：
本文提出DIME框架，解决持续学习中食物类别样本不平衡与新增类别数量不平衡问题，通过轻量适配器和谱合并策略提升效率，实验显示性能提升超3%。
摘要：
现实世界饮食记录中的视觉食物识别自然表现出严重的数据不平衡，其中少量食物类别频繁出现而许多类别罕见，导致长尾类分布。在实践中，食物识别系统通常处于持续学习设置中，新类别随时间逐步引入。然而，现有研究通常假设每个增量步骤引入相似数量的新食物类别，这在现实世界中很少发生，因为新观察到的类别数量在不同步骤中变化显著，导致高度不均衡的学习动态。因此，持续食物识别表现出双重不平衡：每个食物类别内的样本不平衡和每个增量学习步骤中需要学习的新食物类别的数量不平衡。本文引入DIME，一种双不平衡感知的适配器合并框架用于持续食物识别。DIME通过参数高效微调为每个任务学习轻量级适配器，并通过类计数引导的谱合并策略逐步整合它们。一个基于排名的阈值调节机制进一步稳定合并过程，通过保留主导知识并允许自适应更新。最终模型在推理时维护一个合并后的适配器，实现高效部署而无需积累任务特定模块。在我们的步不平衡设置下，实验表明所提方法在现实长尾食物基准上比现有最强的持续学习基线提高了超过3%。代码可在https://github.com/xiaoyanzhang1/DIME获取。
英文摘要：
Visual food recognition in real-world dietary logging scenarios naturally exhibits severe data imbalance, where a small number of food categories appear frequently while many others occur rarely, resulting in long-tailed class distributions. In practice, food recognition systems often operate in a continual learning setting, where new categories are introduced sequentially over time. However, existing studies typically assume that each incremental step introduces a similar number of new food classes, which rarely happens in real world where the number of newly observed categories can vary significantly across steps, leading to highly uneven learning dynamics. As a result, continual food recognition exhibits a dual imbalance: imbalanced samples within each food class and imbalanced numbers of new food classes to learn at each incremental learning step. In this work, we introduce DIME, a Dual-Imbalance-aware Adapter Merging framework for continual food recognition. DIME learns lightweight adapters for each task using parameter-efficient fine-tuning and progressively integrates them through a class-count guided spectral merging strategy. A rank-wise threshold modulation mechanism further stabilizes the merging process by preserving dominant knowledge while allowing adaptive updates. The resulting model maintains a single merged adapter for inference, enabling efficient deployment without accumulating task-specific modules. Experiments on realistic long-tailed food benchmarks under our step-imbalanced setup show that the proposed method consistently improves by more than 3% over the strongest existing continual learning baselines. Code is available at https://github.com/xiaoyanzhang1/DIME.
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。
