论文标题
多视语义一致性的本地流形扩展
Local Manifold Augmentation for Multiview Semantic Consistency
论文作者
论文摘要
多文章自我监督表示从探索复杂类内变化数据的语义一致性方面学习根源。这种变化无法直接访问，因此通过数据增强模拟。但是，通常采用的增强是手工制作的，并限于简单的几何和颜色变化，这些变化无法覆盖丰富的类内变化。在本文中，我们建议从数据集中提取潜在的数据变化，并构建一个新颖的增强操作员，即局部歧管增强（LMA）。 LMA是通过训练实例调节的生成器来实现的，以适合数据的局部流形，并使用它来对多视图进行采样。 LMA显示了创建无限数量数据视图，保留语义的能力，并模拟对象姿势，观点，照明条件，背景等复杂的变化。实验表明，LMA整合，自我讨论的学习方法（例如Mocov2和Simsiam）（例如普遍的基准benchmarks cifar10，cifar10，cifar10，cifar100 ,， cifar10，cifar100 ,，此外，LMA导致表示对观点，物体姿势和照明变化以及对各种真实分布变化的更明显不变性的表示形式，对Imagenet-V2，Imagenet-R，Imagenet-R，Imagenet Sketch等反射的各种真实分布变化都具有更强的鲁棒性。
Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation. Such variation is not directly accessible and therefore simulated by data augmentations. However, commonly adopted augmentations are handcrafted and limited to simple geometrical and color changes, which are unable to cover the abundant intra-class variation. In this paper, we propose to extract the underlying data variation from datasets and construct a novel augmentation operator, named local manifold augmentation (LMA). LMA is achieved by training an instance-conditioned generator to fit the distribution on the local manifold of data and sampling multiview data using it. LMA shows the ability to create an infinite number of data views, preserve semantics, and simulate complicated variations in object pose, viewpoint, lighting condition, background etc. Experiments show that with LMA integrated, self-supervised learning methods such as MoCov2 and SimSiam gain consistent improvement on prevalent benchmarks including CIFAR10, CIFAR100, STL10, ImageNet100, and ImageNet. Furthermore, LMA leads to representations that obtain more significant invariance to the viewpoint, object pose, and illumination changes and stronger robustness to various real distribution shifts reflected by ImageNet-V2, ImageNet-R, ImageNet Sketch etc.
