2 A.1 Effect of UNet layers 2 A.2 Effect of dimensionality reduction 2 A.3 Effect of fusion strategy 2 A.4 Effect of captioner and timestep

To further understand the contributions of each component in our method as well as the impact of various design choices, we conduct a series of ablation studies on the SPair-71k dataset [7]. The quantitative results are reported in terms of PCK at different κ thresholds, and we sample 20 pairs for each category. We report PCK@κ (κ = 0.01, 0.05, 0.10) for each setting and both the Stable Diffusion and Fuse-ViT-B/14 methods. We analyze how features extracted at different layers in the U-Net architecture affect the accuracy, specifically at layers 2, 5, and 8, for the Stable Diffusion (SD) and Fuse-ViT-B/14 methods. The experiment results in Tab. 1 suggest that layer 5 alone provides substantial performance for both the Stable Diffusion and the fused features, while gathering all three layers further improves the overall performance for the fused features.