Convolutional Neural Networks with Alternately Updated Clique

By Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin. 2018

130 citations recorded by the source corpus.

Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique (CliqueNet). In contrast to prior networks, there are both forward and backward connections between any two layers in the same block. The layers are constructed as a loop and are updated alternately. The CliqueNet has some unique properties. For each layer, it is both the input and output of any other layer in the same block, so that the information flow among layers is maximized. During propagation, the newly updated layers are concatenated to re-update previously updated layer, and parameters are reused for multiple times. This recurrent feedback structure is able to bring higher level visual information back to refine low-level filters and achieve spatial attention. We analyze the features generated at different stages and observe that using refined features leads to a better result. We adopt a multiscale feature strategy that effectively avoids the progressive growth of parameters. Experiments on image recognition datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet show that our proposed models achieve the state-of-the-art performance with fewer parameters1.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

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

1. Andrew Zisserman
2. Quoc V. Le
3. Junjie Yan
4. Cordelia Schmid
5. Luc Van Gool
6. Jiashi Feng
7. Mohit Bansal
8. João Carreira

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Ming-Hsuan Yang
4. Ling Shao
5. Wenguan Wang
6. Xiaogang Wang
7. Jianbing Shen
8. Andrew Zisserman

In Model Architectures

1. Junjie Yan
2. Wenguan Wang
3. Jianbing Shen
4. Haibin Ling
5. Quoc V. Le
6. Andrew Zisserman
7. Qifeng Chen
8. Changhu Wang

Citations in the corpus

• Perceiver: General Perception with Iterative Attention (2021, background): “Re-entrant processing of this kind (sometimes referred to as top-down processing) has a long history in computer vision (Borenstein et al., 2004; Kumar et al., 2005; Carreira et al., 2016; Hu & Ramanan, 2016; Yang et al., 2018; Lin et al., 2020).”
• Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis (2020, unknown): “Feedback-Based Architectures, where the full or partial output of a system is routed back into the input as part of an iterative cause-and-effect process (Ford, 1999), have been recently introduced into neural networks (Belagiannis & Zisserman, 2017; Zamir et al., 2017; Yang et al., 2018).”
• Spectral-Spatial Attention Networks for Hyperspectral Image Classification (2019, background): “[43] proposed an attention mechanism to extract additional meaningful information on the transition layer and passed to the next feature extraction block for subsequent feature exploitation.”
• Dynamic Recursive Neural Network (2019, methodology): “Recently, based on the studies about recurrent struc­ ture and iterative refinement [24, 28], densely connected structure is widely used to obtain more efficient model like DenseNet [18] and CliqueNet [43].”
• SOGNet: Scene Overlap Graph Network for Panoptic Segmentation (2019, background): “Convolutional Neural Networks (CNNs) have achieved huge success in computer vision tasks such as image recognition (He et al. 2016; Yang et al. 2018), semantic segmentation (Long, Shelhamer, and Darrell 2015; Chen et al.”
• Context-Gated Convolution (2019, unknown): “[54] proposed an Alternately Updated Clique to introduce feedback mechanisms into CNNs.”
• Expectation-Maximization Attention Networks for Semantic Segmentation (2019, methodology): “ segmentation. Fully convolutional network (FCN) [22] based methods have made great progress in image semantic segmentation by leveraging the powerful convolutional features of classification networks [14,15,33] pre-trained on large-scale data [28]. Several model variants are proposed to enhance the ”
• Involution: Inverting the Inherence of Convolution for Visual Recognition (2021, background): “The topological connectivity [18, 21, 55, 57] and hyperparameter configurations [15, 38, 48] of convolutional neural networks have undergone rapid evolution, but developing brand new operators attracts little attention for crafting innovative architectures.”
• Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “CliqueNet [140] adds bidirectional connections between two arbitrary layers within a block, maximizing the information flow through layers and reusing layer parameters multiple times.”