通过压缩样本增量学习新食品分类
Learning to Classify New Foods Incrementally Via Compressed Exemplars
AI总结：
针对食品图像分类系统因静态数据集无法适配动态食品数据、持续学习中存在灾难性遗忘且内存缓冲区容量有限的问题，提出基于持续学习的神经图像压缩方法扩展缓冲区存储更多样本，在多个数据集上提升了分类准确率，且方法可推广至其他持续学习领域。
摘要：
食品图像分类系统通过基于图像的膳食评估技术，在健康监测和饮食追踪中发挥着关键作用。然而，现有的食品识别系统依赖于静态数据集，这类数据集的特点是具有预定义的固定食品类别数量。这与食品消费的实际情况形成了鲜明对比，现实中的食品数据是不断变化的。因此，食品图像分类系统应当适应并管理持续演化的数据，这正是持续学习发挥重要作用的场景。持续学习中的一个挑战是灾难性遗忘，即机器学习模型在学习新信息时往往会丢弃旧知识。虽然记忆重放算法通过存储旧数据作为样本在缓解该问题上展现出潜力，但它们受限于内存缓冲区的有限容量，导致新数据与先前学习的数据之间存在不平衡。为解决这一问题，本研究探索利用神经图像压缩来扩展缓冲区大小并增强数据多样性。我们提出了持续学习神经压缩模型的概念，以自适应地提升压缩数据的质量，并优化每像素比特率（bpp）从而存储更多样本。我们开展了大量实验，包括在食品专用数据集Food-101、VFN-74以及通用数据集ImageNet-100上的评估，结果表明分类准确率得到了提升。这一进展对于推动更具实用性、能够适应持续演化数据的食品识别系统至关重要。此外，我们提出的原理和方法具有更广泛的应用前景，可将其优势拓展至持续机器学习系统的其他领域。
英文摘要：
Food image classification systems play a crucial role in health monitoring and diet tracking through image-based dietary assessment techniques. However, existing food recognition systems rely on static datasets characterized by a pre-defined fixed number of food classes. This contrasts drastically with the reality of food consumption, which features constantly changing data. Therefore, food image classification systems should adapt to and manage data that continuously evolves. This is where continual learning plays an important role. A challenge in continual learning is catastrophic forgetting, where ML models tend to discard old knowledge upon learning new information. While memory-replay algorithms have shown promise in mitigating this problem by storing old data as exemplars, they are hampered by the limited capacity of memory buffers, leading to an imbalance between new and previously learned data. To address this, our work explores the use of neural image compression to extend buffer size and enhance data diversity. We introduced the concept of continuously learning a neural compression model to adaptively improve the quality of compressed data and optimize the bitrates per pixel (bpp) to store more exemplars. Our extensive experiments, including evaluations on food-specific datasets including Food-101 and VFN-74, as well as the general dataset ImageNet-100, demonstrate improvements in classification accuracy. This progress is pivotal in advancing more realistic food recognition systems that are capable of adapting to continually evolving data. Moreover, the principles and methodologies we've developed hold promise for broader applications, extending their benefits to other domains of continual machine learning systems.
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。
