SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
This work addresses efficiency improvements for isotropic networks in visual recognition, though it is incremental as it builds on existing compression techniques.
The paper tackles the problem of compressing isotropic networks like ConvMixer and vision transformers by evaluating parameter sharing strategies, resulting in a method that compresses ConvMixer by 1.9x while improving accuracy on ImageNet.
Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convolutional neural networks (CNNs). Isotropic architectures are particularly well-suited to cross-layer weight sharing, an effective neural network compression technique. In this paper, we perform an empirical evaluation on methods for sharing parameters in isotropic networks (SPIN). We present a framework to formalize major weight sharing design decisions and perform a comprehensive empirical evaluation of this design space. Guided by our experimental results, we propose a weight sharing strategy to generate a family of models with better overall efficiency, in terms of FLOPs and parameters versus accuracy, compared to traditional scaling methods alone, for example compressing ConvMixer by 1.9x while improving accuracy on ImageNet. Finally, we perform a qualitative study to further understand the behavior of weight sharing in isotropic architectures. The code is available at https://github.com/apple/ml-spin.