• Home
  • Search
  • Active weighted mapping-based residual convolutional neural network for image classification
  • Cite Icon3
  • https://doi.org/10.1007/s11042-020-09808-3Copy DOI Icon

Active weighted mapping-based residual convolutional neural network for image classification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. Results of the extensive experiments show that the proposed method works successfully on the various backbone architectures from ResNet to DenseNet. We also verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.

Similar Papers
  • Conference Article

Research on Image Denoising Based on Dual-Path Multi-scale Feature Fusion Network

  • Dec 09, 2022
  • Mingxu Yin +1
  • Research Article
  • Citations7

Towards an effective model for lung disease classification: Using Dense Capsule Nets for early classification of lung diseases

  • May 31, 2022
  • Applied Soft Computing
  • Faizan Karim +6
  • Research Article
  • Citations4

A Quantitative Insight Into the Role of Skip Connections in Deep Neural Networks of Low Complexity: A Case Study Directed at Fluid Flow Modeling

  • Jul 18, 2022
  • Journal of Computing and Information Science in Engineering
  • Abouzar Choubineh +3
  • Research Article
  • Citations30

Automatic Design of Deep Networks with Neural Blocks

  • Aug 24, 2019
  • Cognitive Computation
  • Guoqiang Zhong +3
  • Video Transcripts

Revisiting the Training of Very Deep Neural Networks without Skip Connections

  • Dec 29, 2020
  • Underline Science Inc.
  • Oyebade Oyedotun
  • Conference Article
  • Citations12

Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting

  • Jan 01, 2021
  • Jireh Jam +5
  • PDF
  • Research Article
  • Citations64

Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network

  • Jan 01, 2022
  • IEEE Access
  • Asghar Ali Chandio +3
  • PDF
  • Research Article
  • Citations1

CMNet: a novel model and design rationale based on comparison studies and synergy of CNN and MetaFormer

  • Sep 22, 2023
  • Machine Vision and Applications
  • Haowen Yu +1
  • Research Article
  • Citations8

YOLO-DSD: A YOLO-Based Detector Optimized for Better Balance between Accuracy, Deployability and Inference Time in Optical Remote Sensing Object Detection

  • Jul 28, 2022
  • Applied Sciences
  • Hengxu Chen +2
  • Book Chapter

Computer Vision, Some Definitions, and Some History

  • Oct 01, 2017
  • Wesley E Snyder +1
  • Research Article
  • Citations30

VARIABILITY IN THREE AREAS OF THE DENCHWORTH SOIL MAP UNIT.

  • Sep 01, 1976
  • Journal of Soil Science
  • C L Bascomb +1
  • Conference Article

Research on Confirming the Weighted Value in Software Quality Model Based on Analytic Hierarchy Process

  • Jan 01, 2015
  • Ruibing Shi +5
  • Dissertation

Improved out-of-distribution for chest X-Ray image quality classification using energy-based methods

  • Jan 01, 2023
  • Guy Marvens Caseneuve
  • PDF
  • Research Article
  • Citations75

Looking for Change? Roll the Dice and Demand Attention

  • Sep 16, 2021
  • Remote Sensing
  • Foivos I Diakogiannis +2
  • Research Article
  • Citations4

Gaze Estimation Network Based on Multi-Head Attention, Fusion, and Interaction.

  • Mar 18, 2025
  • Sensors (Basel, Switzerland)
  • Changli Li +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.