针对长尾分布生成模型中尾部类别表征不足的问题，提出新方法提升生成质量。
Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
- 为每个类别设计独立的重尾学生分布先验，均衡各类别在潜在空间的分布
- 在严重长尾数据上显著降低FID分数，且在每类评估中优于基线模型
- 适合处理极端长尾数据生成，尤其当类别频率比超过5时优势明显
在类别分布不均衡的条件下，使用全局先验的变分自编码器（VAEs）会导致尾部类别在潜在空间中表征不足。尽管$t^3$VAE通过重尾的学生分布先验提升了鲁棒性，但其单一全局先验仍按类别频率分配概率质量。为此，我们提出C-$t^3$VAE，为每个类别设计独立的联合先验，覆盖潜在变量和输出变量，实现类别条件成分间均匀的先验质量分配。我们基于γ-幂散度推导出闭式优化目标，并引入等权重潜在混合用于平衡生成。在SVHN-LT、CIFAR100-LT和CelebA数据集上，当类别极度不均衡时，C-$t^3$VAE始终优于$t^3$VAE和高斯基线模型，且在均衡或轻度不均衡场景下仍具竞争力。在每类F1评分中，该模型在高度不均衡设置下全面超越条件高斯VAE。我们进一步识别出，当类别频率比ρ<5时，高斯模型仍可竞争；而当ρ≥5时，本方法在生成平衡性和模式覆盖上均有提升。
原文摘要 · Abstract (English)
Variational Autoencoders (VAEs) with global priors trained under an imbalanced empirical class distribution can lead to underrepresentation of tail classes in the latent space. While $t^3$VAE improves robustness via heavy-tailed Student's $t$-distribution priors, its single global prior still allocates mass proportionally to class frequency. We address this latent geometric bias by introducing C-$t^3$VAE, which assigns a per-class Student's $t$ joint prior over latent and output variables. This design promotes uniform prior mass across class-conditioned components. To optimize our model we derive a closed-form objective from the $γ$-power divergence, and we introduce an equal-weight latent mixture for class-balanced generation. On SVHN-LT, CIFAR100-LT, and CelebA datasets, C-$t^3$VAE consistently attains lower FID scores than $t^3$VAE and Gaussian-based VAE baselines under severe class imbalance while remaining competitive in balanced or mildly imbalanced settings. In per-class F1 evaluations, our model outperforms the conditional Gaussian VAE across highly imbalanced settings. Moreover, we identify the mild imbalance threshold $ρ< 5$, for which Gaussian-based models remain competitive. However, for $ρ\geq 5$ our approach yields improved class-balanced generation and mode coverage.
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。