LADA：用于持续学习的可扩展标签特定CLIP适配器
LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
AI总结：
针对CLIP持续学习推理时参数选择易错的问题，提出LADA，通过在冻结的CLIP图像编码器后附加轻量级标签特定记忆单元生成判别特征，并采用特征蒸馏防止灾难性遗忘，实现了高效的最先进性能。
摘要：
使用像CLIP这样的视觉-语言模型进行持续学习，通过利用其可迁移的表示，为构建可扩展的机器学习系统提供了一条途径。现有的基于CLIP的方法通过添加多组可学习参数来适应预训练图像编码器，每个任务使用部分参数。这要求在推理时为输入图像选择预期参数，这容易产生错误并降低性能。为了解决这个问题，我们引入了LADA（Label-specific ADApter，标签特定适配器）。LADA没有跨任务划分参数，而是将轻量级的标签特定记忆单元附加到冻结的CLIP图像编码器上，通过聚合任务无关的知识来实现判别性特征生成。为了防止灾难性遗忘，LADA对已见类采用特征蒸馏，防止其特征受到新类的干扰。LADA位于图像编码器之后，阻止了梯度流向冻结的CLIP参数，确保了高效的训练。大量结果表明，LADA在持续学习设置中实现了最先进的性能。实现代码可在https://github.com/MaolinLuo/LADA获取。
英文摘要：
Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding multiple sets of learnable parameters, with each task using a partial set of parameters. This requires selecting the expected parameters for input images during inference, which is prone to error that degrades performance. To address this problem, we introduce LADA (Label-specific ADApter). Instead of partitioning parameters across tasks, LADA appends lightweight, label-specific memory units to the frozen CLIP image encoder, enabling discriminative feature generation by aggregating task-agnostic knowledge. To prevent catastrophic forgetting, LADA employs feature distillation for seen classes, preventing their features from being interfered with by new classes. Positioned after the image encoder, LADA prevents gradient flow to the frozen CLIP parameters, ensuring efficient training. Extensive results show that LADA achieves state-of-the-art performance in continual learning settings. The implementation code is available at https://github.com/MaolinLuo/LADA.
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。
