arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.00514cs.LGcs.CV
收藏

在重建空间中生成,在语义空间中匹配:一步生成的传输几何

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Genentech(基因泰克)

Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, Aviv Regev

AI总结:

本文研究自监督表示学习(SSL)特征在一步生成模型中的作用,提出在语义特征空间中使用Sinkhorn散度进行分布匹配,显著降低ImageNet FID,并揭示了评估指标与训练特征之间的潜在冲突。

摘要:

生成建模和自监督表示学习(SSL)优化结构不同的目标:生成训练奖励分布保真度,而SSL奖励语义一致性。然而,最近的研究反复发现SSL特征改善了生成训练,尽管这种协同作用的机制仍不清楚。在这里,我们在一步生成的框架下研究SSL在生成建模中的优势,其中表示的作用是明确的:冻结的SSL特征用于将生成的样本与真实数据匹配。我们在该特征空间中使用Sinkhorn散度,为Wasserstein距离提供了一个可处理的代理,这是由Fréchet风格评估指标(如FID)近似的总体差异。我们发现,当在语义结构化的SSL特征空间中计算时,这个目标变得非常有效(ImageNet FID降低39倍)。我们将这种行为主要归因于匹配估计:抑制无关重建细节的语义SSL特征诱导出更紧凑的几何结构,使分布匹配更易处理。因此,最佳的训练SSL特征不一定与评估指标使用的特征匹配。特别是,我们表明使用Inception作为特征提取器可以改善FID,同时降低匹配稳定性和样本质量,揭示了一种形式的指标黑客攻击。通过在ImageNet上的大量实验,我们确定了哪些SSL特征族能带来最佳的生成性能,并表明匹配稳定性是选择它们的定量标准。代码可在https://github.com/Genentech/semantic-transport-generation获取。

英文摘要:

Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rewards semantic coherence. Yet recent work repeatedly finds that SSL features improve generative training, though the mechanism of this synergy remains unclear. Here, we study the benefits of SSL in generative modeling in the framework of one-step generation where the role of representation is explicit: frozen SSL features are used to match generated samples to real data. We use the Sinkhorn divergence in that feature space, providing a tractable surrogate for the Wasserstein distance, the population-level discrepancy approximated by Fréchet-style evaluation metrics (such as FID). We find that this objective becomes highly effective when computed in a semantically structured SSL feature space (a 39$\times$ reduction in ImageNet FID). We trace this behavior primarily to matching estimation: semantic SSL features that suppress nuisance reconstruction details induce a more compact geometry, making distribution matching more tractable. As a consequence, the best training SSL features need not match the features used by the evaluation metric. In particular, we show that using Inception as the feature extractor can improve FID while degrading matching stability and sample quality, revealing a form of metric hacking. Using extensive experiments on ImageNet, we identify which SSL feature families lead to best generation performance and show that matching stability is a quantitative criterion for selecting them. Code is available at https://github.com/Genentech/semantic-transport-generation.

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。

↑