Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting old ones. Traditional CIL models are trained from scratch to continually acquire knowledge as data evolves. Recently, pre-training has achieved substantial progress, making vast pre-trained models (PTMs) accessible for CIL. Contrary to traditional methods, PTMs possess generalizable embeddings, which can be easily transferred. In this work, we revisit CIL with PTMs and argue that the core factors in CIL are adaptivity for model updating and generalizability for knowledge transferring. 1) We first reveal that frozen PTM can already provide generalizable embeddings for CIL. Surprisingly, a simple baseline (SimpleCIL) which continually sets the classifiers of PTM to prototype features can beat state-of-the-art even without training on the downstream task. 2) Due to the distribution gap between pre-trained and downstream datasets, PTM can be further cultivated with adaptivity via model adapting. We propose ADapt And Merge (ADAM), which aggregates the embeddings of PTM and adapted models for classifier construction. ADAM is a general framework that can be orthogonally combined with any parameter-efficient tuning method, which holds the advantages of PTM's generalizability and adapted model's adaptivity. 3) Additionally, we find previous benchmarks are unsuitable in the era of PTM due to data overlapping and propose four new benchmarks for assessment, namely ImageNet-A, ObjectNet, OmniBenchmark, and VTAB. Extensive experiments validate the effectiveness of ADAM with a unified and concise framework.
翻译:传统入门学习(CIL)旨在适应新兴新班级,而不会忘记旧班级。传统的CIL模式从零到不断培训,随着数据的变化不断获得知识。最近,培训前取得了长足进展,使CIL能够使用大量的预培训模型。与传统方法相反,PTM拥有可轻易转让的通用嵌入。在这项工作中,我们用PTM重新审视CIL,认为CIL的核心因素是适应模式更新和普及知识转让基准的适应性。1我们首先发现,冻结的PTM能够为CIL提供通用嵌入。令人惊讶的是,一个简单的基线(SOSCIL)已经取得了长足的进展,不断将PTM的分类组组到原型功能。即使没有下游任务的培训,PTM具有最先进的嵌入式嵌入功能。2 由于预先培训和下游数据集之间的分布差距,PTM可以通过模型的适应性来进一步培育。我们提议ADAPT和Merge(ADM)将PTM的嵌入和调整模型与升级的升级模型结合起来,从而提出升级、升级的升级和升级的ADAM的总体框架。</s>