IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification

By Sam Leroux, Pavlo Molchanov, Pieter Simoens, Bart Dhoedt, Thomas Breuel, Jan Kautz. 2018

46 citations recorded by the source corpus.

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding vanishing gradients. These shortcut connections have interesting side-effects that make ResNets behave differently from other typical network architectures. In this work we use these properties to design a network based on a ResNet but with parameter sharing and with adaptive computation time. The resulting network is much smaller than the original network and can adapt the computational cost to the complexity of the input image.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Neurology

In Efficiency & Compression

Citations in the corpus

Dynamic Neural Networks: A Survey (2021, methodology): “Rather than skipping the execution of layers with independent parameters, multiple blocks in each ResNet stage could be replaced by one weight-sharing block, leading to a significant reduction of parameters [66].”
A-ViT: Adaptive Tokens for Efficient Vision Transformer (2021, background): “[27] proposed a residual variant with shared weights and a halting mechanism.”
Deep semantic segmentation of natural and medical images: a review (2019, background): “Several works have been done on reducing the time and the computational complexity of deep classification networks (Howard et al. 2017; Leroux et al. 2018).”
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs (2019, background): “Leroux et al. [23] proposed probably the ﬁrst recurrent architecture that performed well on ImageNet.”