用变分推理做自监督学习，不靠解码器也能高效提取特征。
Variational Self-Supervised Learning
- 双编码器对称结构，用动量更新的教师网络定义动态先验。
- 用跨视图去噪替代重构，提升图像特征表达能力。
- 适合想理解自监督与概率建模结合的研究者或工程师。
我们提出变分自监督学习（VSSL），一种将变分推断与自监督学习结合的新框架，实现高效且无需解码器的表征学习。与依赖输入重构的传统变分自编码器不同，VSSL 对称地耦合两个输出为高斯分布的编码器。一个动量更新的教师网络定义动态、数据相关的先验，学生编码器则从增强视图中生成近似后验。ELBO 中的重构项被跨视图去噪目标替代，保持高斯KL散度的解析可计算性。我们还引入基于余弦的KL和对数似然项公式，增强高维潜在空间中的语义对齐。在CIFAR-10、CIFAR-100和ImageNet-100上的实验表明，VSSL性能可媲美甚至优于领先的自监督方法（如BYOL和MoCo V3）。该方法提供了一种可扩展、基于概率理论的学习可迁移表征的途径，无需生成式重构，弥合了变分建模与现代自监督技术之间的差距。
原文摘要 · Abstract (English)
We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs. A momentum-updated teacher network defines a dynamic, data-dependent prior, while the student encoder produces an approximate posterior from augmented views. The reconstruction term in the ELBO is replaced with a cross-view denoising objective, preserving the analytical tractability of Gaussian KL divergence. We further introduce cosine-based formulations of KL and log-likelihood terms to enhance semantic alignment in high-dimensional latent spaces. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show that VSSL achieves competitive or superior performance to leading self-supervised methods, including BYOL and MoCo V3. VSSL offers a scalable, probabilistically grounded approach to learning transferable representations without generative reconstruction, bridging the gap between variational modeling and modern self-supervised techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。