DeepAI AI Chat
Log In Sign Up

Gated Convolutional Networks with Hybrid Connectivity for Image Classification

by   Chuanguang Yang, et al.

We design a highly efficient architecture called Gated Convolutional Network with Hybrid Connectivity (HCGNet), which is equipped with the combination of local residual and global dense connectivity to enjoy their individual superiorities as well as attention-based gate mechanism to assist feature recalibration. To adapt our hybrid connectivity, we further propose a novel module which includes a squeeze cell for obtaining the compact features from input and then a multi-scale excitation cell attached an update gate to model the global context features for capturing long-range dependency based on multi-scale information. We also locate a forget gate on residual connectivity to decay the reused features, which can be aggergated with newly global context features to form the output that can facilitate effective feature exploration as well as re-exploitation to some extent. Moreover, the number of our proposed modules under dense connectivity can quite fewer than classical DenseNet thus reducing considerable redundancy but with empirically better performance. On CIFAR-10/100 datasets, HCGNets significantly outperform state-of-the-art both human-designed and auto-searched networks with much fewer parameters. It can also consistently obtain better performance and interpretability than widely applied networks in practice on ImageNet dataset.


DCANet: Dense Context-Aware Network for Semantic Segmentation

As the superiority of context information gradually manifests in advance...

PPCR: Learning Pyramid Pixel Context Recalibration Module for Medical Image Classification

Spatial attention mechanism has been widely incorporated into deep convo...

Sequential Cross Attention Based Multi-task Learning

In multi-task learning (MTL) for visual scene understanding, it is cruci...

GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection

Forensic analysis depends on the identification of hidden traces from ma...

Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting

We propose a novel recurrent network-based HDR deghosting method for fus...

Deep Axial Hypercomplex Networks

Over the past decade, deep hypercomplex-inspired networks have enhanced ...

Deep progressive multi-scale attention for acoustic event classification

Convolutional neural network (CNN) is an indispensable building block fo...