自监督学习背后的概率模型
A Probabilistic Model Behind Self-Supervised Learning
AI总结：
提出用于自监督学习的生成式潜变量模型，为判别式SSL提供统一理论框架，并据此开发的SimVAE在需要风格信息的任务中表现更优，推动实现任务无关的表示。
摘要：
在自监督学习（SSL）中，表示是通过没有标注标签的辅助任务来学习的。一个常见的任务是对数据的增强或不同模态进行分类，它们共享语义内容（例如图像中的对象），但在风格上有所不同（例如对象的位置）。已经提出了许多自监督学习方法，例如 SimCLR、CLIP 和 DINO，这些方法最近因其表示实现了与监督学习相当的下游性能而备受关注。然而，对自监督方法的理论理解仍然缺乏。为了解决这个问题，我们提出了一个用于自监督学习的生成式潜变量模型，并表明包括对比方法在内的几类判别式 SSL 会在表示上诱导出可比的分布，为这些方法提供了一个统一的理论框架。所提出的模型还证明了与互信息的联系以及使用“projection head”的合理性。通过生成式拟合模型来学习表示（称为 SimVAE）在简单的图像基准上提高了性能，优于判别式和其他基于 VAE 的方法，并在更复杂的环境中显著缩小了生成式和判别式表示学习之间的差距。重要的是，正如我们的分析所预测的那样，在需要风格信息的自监督学习中，SimVAE 表现更优，在理解自监督方法和实现任务无关的表示方面迈出了重要一步。
英文摘要：
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in an image) but differ in style (e.g. the object's location). Many approaches to self-supervised learning have been proposed, e.g. SimCLR, CLIP, and DINO, which have recently gained much attention for their representations achieving downstream performance comparable to supervised learning. However, a theoretical understanding of self-supervised methods eludes. Addressing this, we present a generative latent variable model for self-supervised learning and show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations, providing a unifying theoretical framework for these methods. The proposed model also justifies connections drawn to mutual information and the use of a ''projection head''. Learning representations by fitting the model generatively (termed SimVAE) improves performance over discriminative and other VAE-based methods on simple image benchmarks and significantly narrows the gap between generative and discriminative representation learning in more complex settings. Importantly, as our analysis predicts, SimVAE outperforms self-supervised learning where style information is required, taking an important step toward understanding self-supervised methods and achieving task-agnostic representations.
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。
