Efficient ConvBN Blocks for Transfer Learning and Beyond
ICLR 2024(2023)
摘要
Convolution-BatchNorm (ConvBN) blocks are integral components in various
computer vision tasks and other domains. A ConvBN block can operate in three
modes: Train, Eval, and Deploy. While the Train mode is indispensable for
training models from scratch, the Eval mode is suitable for transfer learning
and beyond, and the Deploy mode is designed for the deployment of models. This
paper focuses on the trade-off between stability and efficiency in ConvBN
blocks: Deploy mode is efficient but suffers from training instability; Eval
mode is widely used in transfer learning but lacks efficiency. To solve the
dilemma, we theoretically reveal the reason behind the diminished training
stability observed in the Deploy mode. Subsequently, we propose a novel Tune
mode to bridge the gap between Eval mode and Deploy mode. The proposed Tune
mode is as stable as Eval mode for transfer learning, and its computational
efficiency closely matches that of the Deploy mode. Through extensive
experiments in object detection, classification, and adversarial example
generation across 5 datasets and 12 model architectures, we demonstrate
that the proposed Tune mode retains the performance while significantly
reducing GPU memory footprint and training time, thereby contributing efficient
ConvBN blocks for transfer learning and beyond. Our method has been integrated
into both PyTorch (general machine learning framework) and MMCV/MMEngine
(computer vision framework). Practitioners just need one line of code to enjoy
our efficient ConvBN blocks thanks to PyTorch's builtin machine learning
compilers.
更多查看译文
关键词
transfer,learning,tune-mode
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