用于持续与广义零样本学习的元学习属性自交互网络
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning
AI总结：
本文提出元学习属性自交互网络MAIN，结合属性自交互与逆正则化，在不使用未见类属性的情况下实现持续与广义零样本学习，训练速度比生成式方法快100倍以上，并在五个标准数据集上取得领先性能。
摘要：
零样本学习（ZSL）是一种通过利用类别属性将模型泛化到训练期间未见类别的方法，前景广阔，但挑战依然存在。近年来，使用生成模型来对抗对训练中已见类别偏差的方法已推动最先进水平，但这些生成模型训练速度慢或计算开销大。此外，这些生成模型假设每个未见类别的属性向量在训练时先验可用，而这并不总是实际可行。同时，虽然许多先前的ZSL方法假设对未见类别进行一次性适应，但在现实中，世界始终在变化，需要持续调整已部署的模型。未准备好处理顺序数据流的模型很可能遭受灾难性遗忘。我们提出了一种用于持续ZSL的元学习属性自交互网络（MAIN）。通过将使用元学习训练的属性自交互与属性编码器的逆正则化相结合，我们能够在不利用未见类别属性的情况下超越最先进结果，同时训练模型的速度也远快于（>100倍）昂贵的基于生成的方法。我们在五个标准ZSL数据集（CUB、aPY、AWA1、AWA2和SUN）上，在广义零样本学习和持续（固定/动态）零样本学习设置下通过实验证明了这一点。广泛的消融和分析证明了所提出的各个组件的有效性。
英文摘要：
Zero-shot learning (ZSL) is a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges remain. Recently, methods using generative models to combat bias towards classes seen during training have pushed state of the art, but these generative models can be slow or computationally expensive to train. Also, these generative models assume that the attribute vector of each unseen class is available a priori at training, which is not always practical. Additionally, while many previous ZSL methods assume a one-time adaptation to unseen classes, in reality, the world is always changing, necessitating a constant adjustment of deployed models. Models unprepared to handle a sequential stream of data are likely to experience catastrophic forgetting. We propose a Meta-learned Attribute self-Interaction Network (MAIN) for continual ZSL. By pairing attribute self-interaction trained using meta-learning with inverse regularization of the attribute encoder, we are able to outperform state-of-the-art results without leveraging the unseen class attributes while also being able to train our models substantially faster (>100x) than expensive generative-based approaches. We demonstrate this with experiments on five standard ZSL datasets (CUB, aPY, AWA1, AWA2, and SUN) in the generalized zero-shot learning and continual (fixed/dynamic) zero-shot learning settings. Extensive ablations and analyses demonstrate the efficacy of various components proposed.
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。
