Timezone: »

Efficient Equivariant Network
Lingshen He · Yuxuan Chen · zhengyang shen · Yiming Dong · Yisen Wang · Zhouchen Lin

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @
Convolutional neural networks (CNNs) have dominated the field of Computer Vision and achieved great success due to their built-in translation equivariance. Group equivariant CNNs (G-CNNs) that incorporate more equivariance can significantly improve the performance of conventional CNNs. However, G-CNNs are faced with two major challenges: \emph{spatial-agnostic problem} and \emph{expensive computational cost}. In this work, we propose a general framework of previous equivariant models, which includes G-CNNs and equivariant self-attention layers as special cases. Under this framework, we explicitly decompose the feature aggregation operation into a kernel generator and an encoder, and decouple the spatial and extra geometric dimensions in the computation. Therefore, our filters are essentially dynamic rather than being spatial-agnostic. We further show that our \emph{E}quivariant model is parameter \emph{E}fficient and computation \emph{E}fficient by complexity analysis, and also data \emph{E}fficient by experiments, so we call our model $E^4$-Net. Extensive experiments verify that our model can significantly improve previous works with smaller model size.Especially, under the setting of training on $1/5$ data of CIFAR10, our model improves G-CNNs by $5\%+$ accuracy,while using only $56\%$ parameters and $68\%$ FLOPs.

Author Information

Lingshen He (Peking University)
Yuxuan Chen (University of Electronic Science and Technology of China)
zhengyang shen (Peking University)
Yiming Dong (Peking University)
Yisen Wang (Peking University)
Zhouchen Lin (Peking University)

More from the Same Authors