LGAIAug 11, 2025

Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation

arXiv:2508.09223v1h-index: 3
Originality Incremental advance
AI Analysis

This work addresses distribution shifts in test-time adaptation for machine learning models, offering an incremental improvement over existing methods.

The paper tackles the problem of test-time adaptation for pretrained models under distribution shifts by proposing Hi-Vec, a method that uses hierarchical layers and dynamic selection to improve robustness, resulting in enhanced performance on multiple datasets.

Test-time adaptation allows pretrained models to adjust to incoming data streams, addressing distribution shifts between source and target domains. However, standard methods rely on single-dimensional linear classification layers, which often fail to handle diverse and complex shifts. We propose Hierarchical Adaptive Networks with Task Vectors (Hi-Vec), which leverages multiple layers of increasing size for dynamic test-time adaptation. By decomposing the encoder's representation space into such hierarchically organized layers, Hi-Vec, in a plug-and-play manner, allows existing methods to adapt to shifts of varying complexity. Our contributions are threefold: First, we propose dynamic layer selection for automatic identification of the optimal layer for adaptation to each test batch. Second, we propose a mechanism that merges weights from the dynamic layer to other layers, ensuring all layers receive target information. Third, we propose linear layer agreement that acts as a gating function, preventing erroneous fine-tuning by adaptation on noisy batches. We rigorously evaluate the performance of Hi-Vec in challenging scenarios and on multiple target datasets, proving its strong capability to advance state-of-the-art methods. Our results show that Hi-Vec improves robustness, addresses uncertainty, and handles limited batch sizes and increased outlier rates.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes