用预训练生成模型反向生成，无监督学视觉特征，效果领先。
Pretrained Reversible Generation as Unsupervised Visual Representation Learning
- 反向生成预训练模型，提取无监督视觉特征
- 64×64图像下ImageNet上达78%准确率，性能领先
- 可灵活选择特征层次，适合各类下游任务
基于分数匹配和流匹配的生成模型在生成任务上取得显著进展，但在判别任务中的潜力仍待挖掘。以往的生成分类器因设计复杂，未能充分发挥这些模型的能力。本文提出预训练可逆生成（PRG），通过反转预训练连续生成模型的生成过程，提取无监督表示。PRG有效复用高容量生成模型，将其作为鲁棒且通用的下游任务特征提取器，并支持根据具体任务灵活选择特征层级。在多个基准测试中，本方法持续优于先前方法，成为基于生成模型的最新最优方案，64×64分辨率下在ImageNet上达到78%的Top-1准确率。大量消融实验及分布外评估进一步验证了其有效性。代码已开源。
原文摘要 · Abstract (English)
Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous generation model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. This framework enables the flexible selection of feature hierarchies tailored to specific downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model based methods, including 78% top-1 accuracy on ImageNet at a resolution of 64*64. Extensive ablation studies, including out-of-distribution evaluations, further validate the effectiveness of our approach.PRG is available at https://github.com/opendilab/PRG.
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。