We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data. LAVA builds on a few recent innovations to enable adapting to partially labelled datasets with class and domain shifts. First, LAVA learns self-supervised visual representations on the source dataset and ground them using class label semantics to overcome transfer collapse problems associated with supervised pretraining. Secondly, LAVA maximises the gains from unlabelled target data via a novel method which uses multi-crop augmentations to obtain highly robust pseudo-labels. By combining these ingredients, LAVA achieves a new state-of-the-art on ImageNet semi-supervised protocol, as well as on 7 out of 10 datasets in multi-domain few-shot learning on the Meta-dataset. Code and models are made available.
翻译:我们提出LAVA,这是使用有限数据进行多域视觉传输学习的简单而有效的方法。LAVA以最近的一些创新为基础,能够适应部分标签的数据集,进行阶级和域变换。首先,LAVA在源数据集上学习了自我监督的视觉表现,并使用类标签语义来克服与受监督的训练前训练有关的传输崩溃问题。第二,LAVA通过一种新颖的方法,利用多作物增殖来获取高度可靠的假标签,将无标签目标数据带来的收益最大化。通过将这些要素结合起来,LAVA在图像网络的半监督协议上实现了一个新的最先进的艺术,并在多领域少见的关于元数据集的10个数据集中实现了7个数据集。提供了各种代码和模型。