带卷积的无样本持续Transformer
Exemplar-Free Continual Transformer with Convolutions
AI总结：
针对视觉Transformer持续学习方法需存样本或推理要任务ID的问题，提出无样本方法ConTraCon，用卷积重加权Transformer注意力权重降参数量，结合增强熵法识别任务，实验显示其以更少参数超多个对比方法。
摘要：
持续学习（CL）指以序列方式训练机器学习模型，使其在无过往训练数据的情况下学习新信息，同时保留先前习得的任务能力。尽管持续学习已受到广泛关注，但计算机视觉领域最新的多数持续学习方法仅聚焦于卷积架构。然而，随着视觉Transformer近期取得成功，有必要挖掘其在持续学习中的潜力。虽已有部分针对视觉Transformer的持续学习方法，但它们要么存储先前任务的训练实例，要么在测试阶段需要任务标识符，存在局限性。\n本文提出一种名为ConTraCon的新型无样本类别/任务增量学习方法，推理阶段无需显式提供任务ID，且无需存储过往训练实例。该方法利用Transformer架构，对在相似任务上训练的Transformer的多头自注意力层的键、查询、值权重进行重加权，重加权过程通过卷积实现，使每个任务的参数量需求维持在较低水平。此外，采用基于图像增强的熵任务识别方法，在推理无需任务ID的情况下预测任务。在四个基准数据集上的实验表明，该方法在参数量更少的前提下，性能优于多种主流对比方法。
英文摘要：
Continual Learning (CL) involves training a machine learning model in a sequential manner to learn new information while retaining previously learned tasks without the presence of previous training data. Although there has been significant interest in CL, most recent CL approaches in computer vision have focused on convolutional architectures only. However, with the recent success of vision transformers, there is a need to explore their potential for CL. Although there have been some recent CL approaches for vision transformers, they either store training instances of previous tasks or require a task identifier during test time, which can be limiting. This paper proposes a new exemplar-free approach for class/task incremental learning called ConTraCon, which does not require task-id to be explicitly present during inference and avoids the need for storing previous training instances. The proposed approach leverages the transformer architecture and involves re-weighting the key, query, and value weights of the multi-head self-attention layers of a transformer trained on a similar task. The re-weighting is done using convolution, which enables the approach to maintain low parameter requirements per task. Additionally, an image augmentation-based entropic task identification approach is used to predict tasks without requiring task-ids during inference. Experiments on four benchmark datasets demonstrate that the proposed approach outperforms several competitive approaches while requiring fewer parameters.
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。
