Attention Based Pruning for Shift Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Attention Based Pruning for Shift Networks


In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in order to reach state-of-the-art accuracy, thus resulting in complex and demanding systems that are poorly fitted to resource-limited devices. Recently, methods have been proposed to replace the generic convolution operator by the combination of a shift operation and a simpler 1x1 convolution. The resulting block, called Shift Layer (SL), is an efficient alternative to CLs in the sense it allows to reach similar accuracies on various tasks with faster computations and fewer parameters. In this contribution, we introduce Shift Attention Layers (SALs), which extend SLs by using an attention mechanism that learns which shifts are the best at the same time the network function is trained. We demonstrate SALs are able to outperform vanilla SLs (and CLs) on various object recognition benchmarks while significantly reducing the number of float operations and parameters for the inference.
Fichier principal
Vignette du fichier
Attention Based Pruning for Shift Networks.pdf (506.58 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03238771 , version 1 (30-07-2021)



Ghouthi Boukli Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio. Attention Based Pruning for Shift Networks. ICPR 2020: 25th International Conference on Pattern Recognition, Jan 2021, Milan (virtual), Italy. pp.4054-4061, ⟨10.1109/ICPR48806.2021.9412859⟩. ⟨hal-03238771⟩
90 View
55 Download



Gmail Facebook Twitter LinkedIn More