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 2310.07756cs.LG
收藏

从随机数据投影器中进行自监督表示学习

Self-supervised Representation Learning From Random Data Projectors

Layer 6 AI(第六层人工智能公司);Dalhousie University(达尔豪斯大学)

Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs

AI总结:

本文提出一种不依赖数据增强或掩码的自监督表示学习方法,通过重建随机数据投影来学习高质量表示,适用于任意数据模态与网络架构,并在多任务中优于现有基线。

摘要:

自监督表示学习(SSRL)通过利用人工设计数据增强下的变换不变性假设,取得了显著进展。尽管基于增强的SSRL算法在计算机视觉和自然语言处理中突破了性能边界,但它们通常无法直接应用于其他数据模态,并可能与特定应用的数据增强约束相冲突。本文提出了一种SSRL方法,可应用于任何数据模态和网络架构,因为它不依赖增强或掩码。具体而言,我们表明可以通过重建随机数据投影来学习高质量数据表示。我们在涵盖多种模态和现实世界应用的广泛表示学习任务上评估了该方法。结果表明,它优于多个最先进的SSRL基线。由于其广泛的适用性和强大的实证结果,我们认为从随机性中学习是一个值得关注的 fruitful 研究方向。

英文摘要:

Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms push the boundaries of performance in computer vision and natural language processing, they are often not directly applicable to other data modalities, and can conflict with application-specific data augmentation constraints. This paper presents an SSRL approach that can be applied to any data modality and network architecture because it does not rely on augmentations or masking. Specifically, we show that high-quality data representations can be learned by reconstructing random data projections. We evaluate the proposed approach on a wide range of representation learning tasks that span diverse modalities and real-world applications. We show that it outperforms multiple state-of-the-art SSRL baselines. Due to its wide applicability and strong empirical results, we argue that learning from randomness is a fruitful research direction worthy of attention and further study.

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。

↑