建设性同化：通过视图生成策略提升对比学习性能
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies
AI总结：
提出将生成视图与专家变换进行建设性同化的方法，在三个数据集上提升对比学习性能约3.6%，并系统分析了视图生成与同化策略的有效性。
摘要：
基于领域专业知识的变换（专家变换），如随机缩放裁剪和颜色抖动，已被证明对 SimCLR 等对比学习技术的成功至关重要。近期，已有若干尝试旨在用学习到的生成视图来替代这些特定领域、人工设计的变换。然而对于图像数据，迄今为止这些视图生成方法均未能超越专家变换。在本研究中，我们探讨一个不同的问题：与其用生成视图替代专家变换，我们能否将生成视图与专家变换进行建设性同化？我们对这一问题给出了肯定回答，并提出了一种视图生成方法和一种简单有效的同化方法，二者结合在三个不同数据集上将最先进水平提升了约 3.6%。重要的是，我们进行了详细的实证研究，系统分析了多种视图生成与同化方法，全面揭示了学习视图在对比表示学习中的有效性。
英文摘要：
Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techniques such as SimCLR. Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned. However for imagery data, so far none of these view-generation methods has been able to outperform expert transformations. In this work, we tackle a different question: instead of replacing expert transformations with generated views, can we constructively assimilate generated views with expert transformations? We answer this question in the affirmative and propose a view generation method and a simple, effective assimilation method that together improve the state-of-the-art by up to ~3.6% on three different datasets. Importantly, we conduct a detailed empirical study that systematically analyzes a range of view generation and assimilation methods and provides a holistic picture of the efficacy of learned views in contrastive representation learning.
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。
