arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.03552cs.CVcs.LG
收藏

一种嵌入式动态的自监督学习方法

An Embedding-Dynamic Approach to Self-supervised Learning

NAVER Clova;Korea University(高丽大学)

Suhong Moon, Domas Buracas, Seunghyun Park, Jinkyu Kim, John Canny

摘要:

许多最近的自监督学习方法在图像分类和其他任务上表现出令人印象深刻的性能。人们使用了各种各样的技术,有些令人困惑,但并不总是清楚地了解它们的好处,特别是当它们结合使用时。在这里,我们把图像的嵌入作为点粒子,并考虑模型优化作为一个动态的过程中,这个系统的粒子。我们的动力学模型结合了相似图像的吸引力,避免局部崩溃的局部分散力,以及实现粒子全局均匀分布的全局分散力。动态视角突出了使用延迟参数图像嵌入(a la BYOL)以及同一图像的多个视图的优点。它还使用了一个纯动态的局部色散力(布朗运动),表现出比其他方法更好的性能,并且不需要其他粒子坐标的知识。该方法被称为MSBReg,它代表(i)多视图质心损失,其施加吸引力以将不同的图像视图嵌入拉向其质心,(ii)奇异值损失,其将粒子系统推向空间均匀密度,(iii)布朗扩散损失。我们评估了MSBReg在ImageNet上的下游分类性能以及迁移学习任务,包括细粒度分类,多类对象分类,目标检测和实例分割。此外,我们还表明,将我们的正则化项应用于其他方法,通过防止模式坍塌,进一步提高了它们的性能并稳定了训练。

英文摘要:

A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a globally-homogeneous distribution of particles. The dynamic perspective highlights the advantage of using a delayed-parameter image embedding (a la BYOL) together with multiple views of the same image. It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates. The method is called MSBReg which stands for (i) a Multiview centroid loss, which applies an attractive force to pull different image view embeddings toward their centroid, (ii) a Singular value loss, which pushes the particle system toward spatially homogeneous density, (iii) a Brownian diffusive loss. We evaluate downstream classification performance of MSBReg on ImageNet as well as transfer learning tasks including fine-grained classification, multi-class object classification, object detection, and instance segmentation. In addition, we also show that applying our regularization term to other methods further improves their performance and stabilize the training by preventing a mode collapse.

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。

↑