Interleaved Structured Sparse Convolutional Neural Networks

By Guotian Xie, Jingdong Wang, Ting Zhang, J. Lai, Richang Hong, Guo-Jun Qi. 2018

110 citations recorded by the source corpus.

In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels, the product of structured sparse kernels, which is a framework for interpreting the recently-developed interleaved group convolutions (IGC) and its variants (e.g., Xception), has been attracting increasing interests. Motivated by the observation that the convolutions contained in a group convolution in IGC can be further decomposed in the same manner, we present a modularized building block, IGC-V2: interleaved structured sparse convolutions. It generalizes interleaved group convolutions, which is composed of two structured sparse kernels, to the product of more structured sparse kernels, further eliminating the redundancy. We present the complementary condition and the balance condition to guide the design of structured sparse kernels, obtaining a balance among three aspects: model size, computation complexity and classification accuracy. Experimental results demonstrate the advantage on the balance among these three aspects compared to interleaved group convolutions and Xception, and competitive performance compared to other state-of-the-art architecture design methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

Citations in the corpus

Efficient Structured Pruning and Architecture Searching for Group Convolution (2018, background): “[50, 49, 44] permute by interleaving channels from different groups, which is also called channel shuffle.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, background): “The differences include: (1) Our fusion outputs four-resolution representations other than only one, and (2) our fusion modules are repeated several times which is inspired by deep fusion [129], [143], [155], [178], [184].”
Deep High-Resolution Representation Learning for Human Pose Estimation (2019, background): “Our approach repeats multi-scale fusion, which is partially inspired by deep fusion and its extensions [65, 71, 57, 77, 79].”
OCNet: Object Context Network for Scene Parsing (2018, neutral): “, 2018) and Interleaved Group Convolution (Xie et al., 2018; Zhang et al., 2017b).”
Fully Learnable Group Convolution for Acceleration of Deep Neural Networks (2019, background): “Differently, the group convolution speed up the network by dividing all ﬁl-ters into several groups, such as [21, 34, 40, 45, 41, 46].”
RC-DARTS: Resource Constrained Differentiable Architecture Search (2019, background): “rformance on mobile devices with limited computational resources. Among these lightweight models, group convolution and its variants play critical roles in improving models’ eciency. The IGCV models [38, 35] introduce novel interleaved group convolutions to improve the representation capablilities o”
OCNet: Object Context for Semantic Segmentation (2021, methodology): “Our interlaced sparse self-attention scheme is different from both CGNL and RCCA through factorizing the dense relation matrix to two sparse relation matrices, and we ﬁnd that similar mechanisms have been applied in the previous studies on network architecture design including ShufﬂeNet (Ma et al. 2”
Lite-HRNet: A Lightweight High-Resolution Network (2021, methodology): “To reduce the complexity, grouping 1 × 1 convolutions with channel shuffling [53, 28] or interleaving [52, 46, 37] are used to keep information exchange across channels.”
Neural Architecture Search for Lightweight Non-Local Networks (2020, background): “There are a lot of handcrafted neural network architectures [19, 42, 17, 30, 45, 25] for mobile applications.”