HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification

While test-time fine-tuning is beneficial in cross-domain few-shot classification, the need for multiple backpropagation steps can be prohibitively expensive in resource-constrained environments. We propose HyperFlow, a gradient-free test-time adaptation method that amortizes fine-tuning dynamics into a lightweight conditional drift network. During offline training, HyperFlow learns from fine-tuning trajectories collected on meta-training tasks. Once trained, it adapts a selected PEFT parameter subspace for a new task by numerical ODE solving, requiring only forward passes of the drift network and no test-time backpropagation through the target model. In experiments on Meta-Dataset and CD-FSL benchmarks, our method improves out-of-domain performance over the direct transfer approach while using only 6-14% of peak memory and about 1% of the FLOPs of standard fine-tuning, positioning HyperFlow as an accuracy–efficiency trade-off between direct transfer and fine-tuning.