计算机科学
安全性令牌
频域
核(代数)
人工智能
人工神经网络
计算机工程
计算机视觉
计算机网络
数学
组合数学
作者
Zhipeng Huang,Zhizheng Zhang,Cuiling Lan,Zheng-Jun Zha,Yan Lü,Baining Guo
标识
DOI:10.1109/iccv51070.2023.00556
摘要
Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, especially on mobile devices, still suffer from noteworthy challenges due to the heavy computational costs of self-attention mechanisms, large kernels, or fully connected layers. In this work, we apply conventional convolution theorem to deep learning for addressing this and reveal that adaptive frequency filters can serve as efficient global token mixers. With this insight, we propose Adaptive Frequency Filtering (AFF) token mixer. This neural operator transfers a latent representation to the frequency domain via a Fourier transform and performs semantic-adaptive frequency filtering via an elementwise multiplication, which mathematically equals to a token mixing operation in the original latent space with a dynamic convolution kernel as large as the spatial resolution of this latent representation. We take AFF token mixers as primary neural operators to build a lightweight neural network, dubbed AFFNet. Extensive experiments demonstrate the effectiveness of our proposed AFF token mixer and show that AFFNet achieve superior accuracy and efficiency trade-offs compared to other lightweight network designs on broad visual tasks, including visual recognition and dense prediction tasks. Code is available at https://github.com/microsoft/TokenMixers.
科研通智能强力驱动
Strongly Powered by AbleSci AI