SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916662856384512 |
|---|---|
| author | Ma, Ke Tang, Jiaqi Guo, Bin Dang, Fan Liu, Sicong Zhu, Zhui Wu, Lei Fang, Cheng Chen, Ying-Cong Yu, Zhiwen Liu, Yunhao |
| author_facet | Ma, Ke Tang, Jiaqi Guo, Bin Dang, Fan Liu, Sicong Zhu, Zhui Wu, Lei Fang, Cheng Chen, Ying-Cong Yu, Zhiwen Liu, Yunhao |
| contents | Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements during fully test-time adaptation (FTTA) without relying on specific network architectures or modifications to the original training procedure. Specifically, we propose a novel dynamic activation sparsity strategy that directly prunes activations at layer-specific dynamic ratios during adaptation, allowing for flexible control of learning ability and memory cost in a data-sensitive manner. Among this, two metrics, Gradient Importance and Layer Activation Memory, are considered to determine the layer-wise pruning ratios, reflecting accuracy contribution and memory efficiency, respectively. Experimentally, our method surpasses the baselines by not only reducing memory usage but also achieving superior accuracy, delivering SOTA performance across diverse datasets, architectures, and tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity Ma, Ke Tang, Jiaqi Guo, Bin Dang, Fan Liu, Sicong Zhu, Zhui Wu, Lei Fang, Cheng Chen, Ying-Cong Yu, Zhiwen Liu, Yunhao Computer Vision and Pattern Recognition Machine Learning Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements during fully test-time adaptation (FTTA) without relying on specific network architectures or modifications to the original training procedure. Specifically, we propose a novel dynamic activation sparsity strategy that directly prunes activations at layer-specific dynamic ratios during adaptation, allowing for flexible control of learning ability and memory cost in a data-sensitive manner. Among this, two metrics, Gradient Importance and Layer Activation Memory, are considered to determine the layer-wise pruning ratios, reflecting accuracy contribution and memory efficiency, respectively. Experimentally, our method surpasses the baselines by not only reducing memory usage but also achieving superior accuracy, delivering SOTA performance across diverse datasets, architectures, and tasks. |
| title | SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.20354 |