IIRC：增量隐式细化分类
IIRC: Incremental Implicitly-Refined Classification
摘要：
我们引入了“增量隐式细化分类（IIRC）”设置，这是对类增量学习设置的扩展，其中传入的类批次具有两个粒度级别。也就是说，每个样本可以具有高级别（粗）标签如“熊”和低级别（细）标签如“北极熊”。一次只提供一个标签，如果模型已经学习了另一个标签，则必须找出另一个标签。这种设置更符合现实生活中的场景，其中学习者通常与同一个实体家族多次交互，发现更多关于它们的粒度，同时仍然试图不忘记以前的知识。此外，这种设置可以评估一些重要的终身学习挑战的模型，这些挑战在现有设置下无法轻松解决。这些挑战可以通过以下例子来激发：“如果一个模型在一个任务中训练熊类，而在另一个任务中训练北极熊类，它会忘记熊的概念吗？它会正确地推断北极熊仍然是熊吗？它会不会错误地将北极熊的标签与其他熊种联系起来？".我们开发了一个标准化的基准测试，可以在IIRC设置上评估模型。我们评估了几种最先进的终身学习算法，并强调了它们的优势和局限性。例如，基于蒸馏的方法表现相对较好，但容易错误地预测每个图像的标签太多。我们希望建议的架构和基准能为从业员提供一个有意义的问题设定
英文摘要：
We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two granularity levels. i.e., each sample could have a high-level (coarse) label like "bear" and a low-level (fine) label like "polar bear". Only one label is provided at a time, and the model has to figure out the other label if it has already learnfed it. This setup is more aligned with real-life scenarios, where a learner usually interacts with the same family of entities multiple times, discovers more granularity about them, while still trying not to forget previous knowledge. Moreover, this setup enables evaluating models for some important lifelong learning challenges that cannot be easily addressed under the existing setups. These challenges can be motivated by the example "if a model was trained on the class bear in one task and on polar bear in another task, will it forget the concept of bear, will it rightfully infer that a polar bear is still a bear? and will it wrongfully associate the label of polar bear to other breeds of bear?". We develop a standardized benchmark that enables evaluating models on the IIRC setup. We evaluate several state-of-the-art lifelong learning algorithms and highlight their strengths and limitations. For example, distillation-based methods perform relatively well but are prone to incorrectly predicting too many labels per image. We hope that the proposed setup, along with the benchmark, would provide a meaningful problem setting to the practitioners
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。
