CAGS: Class-Adaptive Guidance Strength for Training-Free Diffusion-Based Dataset Distillation

Training-free diffusion-based dataset distillation methods such as MGD${}^3$ typically use a single classifier-free guidance (CFG) strength for all classes. This class-agnostic design overlooks substantial variation in class complexity: structurally diverse classes may be under-guided, whereas simpler classes can suffer from excessive sharpening. Our key insight is that class-wise generation statistics can reveal how strongly each class should be guided. Based on this observation, we propose CAGS (Class-Adaptive Guidance Strength), a training-free method that assigns a class-specific CFG strength using cluster entropy and intra-class variance. A systematic ablation and weight search over an initial four-factor design shows that these two factors consistently drive the gains, while mode count and inter-class separability can be removed. We further provide a theoretical explanation under a Gaussian-mixture model, where the optimal guidance satisfies $$\begin{gathered} lambd{a}_c^{\ast } \\ propto{v}_c/ \\ sigm{a}_c^2 \end{gathered}$$ and increases with both intra-class variance and entropy; consequently, the benefit of adaptation grows with cross-class heterogeneity. On ImageNet-100 at IPC=10, CAGS achieves 30.81% on ResNet-18, 29.74% on ResNetAP-10, and 25.55% on ConvNet-6, improving over MGD${}^3$ by 7.21, 3.94, and 2.15 percentage points, respectively, and outperforming other published baselines including IDC-1 and MinMaxDiff. In matched scaling experiments, the gains increase to 3.58–6.97 points on ImageNet-1000, while remaining near-neutral on a low-heterogeneity 10-class subset and reaching +5.28 points on ImageNette. CAGS also generalizes across generators, improving Stable Diffusion 1.5 results on Food-101 from 2.27% to 4.17%, with zero trainable parameters and negligible inference overhead.