Test-Time Model Adaptation with Only Forward Passes
arxiv(2024)
摘要
Test-time adaptation has proven effective in adapting a given trained model
to unseen test samples with potential distribution shifts. However, in
real-world scenarios, models are usually deployed on resource-limited devices,
e.g., FPGAs, and are often quantized and hard-coded with non-modifiable
parameters for acceleration. In light of this, existing methods are often
infeasible since they heavily depend on computation-intensive backpropagation
for model updating that may be not supported. To address this, we propose a
test-time Forward-Only Adaptation (FOA) method. In FOA, we seek to solely learn
a newly added prompt (as model's input) via a derivative-free covariance matrix
adaptation evolution strategy. To make this strategy work stably under our
online unsupervised setting, we devise a novel fitness function by measuring
test-training statistic discrepancy and model prediction entropy. Moreover, we
design an activation shifting scheme that directly tunes the model activations
for shifted test samples, making them align with the source training domain,
thereby further enhancing adaptation performance. Without using any
backpropagation and altering model weights, FOA runs on quantized 8-bit ViT
outperforms gradient-based TENT on full-precision 32-bit ViT, while achieving
an up to 24-fold memory reduction on ImageNet-C. The source code will be
released.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要