CroMo-Mixup：为持续自监督学习增强跨模型表示
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
AI总结：
针对持续自监督学习中的任务混淆问题，提出CroMo-Mixup框架，通过跨任务数据混合和跨模型特征混合增强负样本多样性与旧知识检索，在多个数据集上提升任务ID预测和平均线性准确率。
摘要：
持续自监督学习（CSSL）在无标注数据上顺序学习一系列任务。持续学习面临的两大挑战是灾难性遗忘和任务混淆。虽然已有研究针对灾难性遗忘挑战，但鲜有工作处理任务混淆问题。在本工作中，我们通过大量实验表明，自监督学习（SSL）可能使CSSL更容易受到任务混淆问题的影响，特别是在类增量学习的多样性较低设置中，因为属于不同任务的不同类别不会同时训练。受此挑战启发，我们提出了一种新颖的跨模型特征混合（CroMo-Mixup）框架，通过两个关键组件解决此问题：1）跨任务数据混合（Cross-Task data Mixup），混合跨任务的样本以增强负样本多样性；2）跨模型特征混合（Cross-Model feature Mixup），学习从当前和旧模型获得的混合样本与原始图像的嵌入之间的相似性，促进跨任务类别对比学习和旧知识检索。我们在三个数据集CIFAR10、CIFAR100和tinyImageNet上，在不同的类增量学习设置下，评估了CroMo-Mixup在提升任务ID预测和所有任务的平均线性准确率方面的有效性。我们验证了CroMo-Mixup在四种最先进的SSL目标上的兼容性。代码可在https://github.com/ErumMushtaq/CroMo-Mixup获取。
英文摘要：
Continual self-supervised learning (CSSL) learns a series of tasks sequentially on the unlabeled data. Two main challenges of continual learning are catastrophic forgetting and task confusion. While CSSL problem has been studied to address the catastrophic forgetting challenge, little work has been done to address the task confusion aspect. In this work, we show through extensive experiments that self-supervised learning (SSL) can make CSSL more susceptible to the task confusion problem, particularly in less diverse settings of class incremental learning because different classes belonging to different tasks are not trained concurrently. Motivated by this challenge, we present a novel cross-model feature Mixup (CroMo-Mixup) framework that addresses this issue through two key components: 1) Cross-Task data Mixup, which mixes samples across tasks to enhance negative sample diversity; and 2) Cross-Model feature Mixup, which learns similarities between embeddings obtained from current and old models of the mixed sample and the original images, facilitating cross-task class contrast learning and old knowledge retrieval. We evaluate the effectiveness of CroMo-Mixup to improve both Task-ID prediction and average linear accuracy across all tasks on three datasets, CIFAR10, CIFAR100, and tinyImageNet under different class-incremental learning settings. We validate the compatibility of CroMo-Mixup on four state-of-the-art SSL objectives. Code is available at \url{https://github.com/ErumMushtaq/CroMo-Mixup}.
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。
