• Home
  • Search
  • MEDA: Multi-output Encoder-Decoder for Spatial Attention in Convolutional Neural Networks
  • Cite Icon5
  • https://doi.org/10.1109/ieeeconf44664.2019.9048981Copy DOI Icon

MEDA: Multi-output Encoder-Decoder for Spatial Attention in Convolutional Neural Networks

  • Nov 1, 2019
  • Huayu Li +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Utilizing channel-wise spatial attention mechanisms to emphasize special parts of an input image is an effective method to improve the performance of convolutional neural networks (CNNs). There are multiple effective implementations of attention mechanism. One is adding squeeze-and-excitation (SE) blocks to the CNN structure that selectively emphasize the most informative channels and suppress the relatively less informative channels by taking advantage of channel dependence. Another method is adding convolutional block attention module (CBAM) to implement both channel-wise and spatial attention mechanisms to select important pixels of the feature maps while emphasizing informative channels. In this paper, we propose an encoder-decoder architecture based on the idea of letting the channel-wise and spatial attention blocks share the same latent space representation. Instead of separating the channel-wise and spatial attention modules into two independent parts in CBAM, we combine them into one encoder-decoder architecture with two outputs. To evaluate the performance of the proposed algorithm, we apply it to different CNN architectures and test it on image classification and semantic segmentation. Through comparing the resulting structure equipped with MEDA blocks against other attention module, we show that the proposed method achieves better performance across different test scenarios.

Similar Papers
  • PDF
  • Research Article
  • Citations36

One Spatio-Temporal Sharpening Attention Mechanism for Light-Weight YOLO Models Based on Sharpening Spatial Attention

  • Nov 28, 2021
  • Sensors (Basel, Switzerland)
  • Mengfan Xue +4
  • Research Article
  • Citations24

3D mineral prospectivity modeling in the Sanshandao goldfield, China using the convolutional neural network with attention mechanism

  • Dec 31, 2023
  • Ore Geology Reviews
  • Zhankun Liu +8
  • PDF
  • Research Article
  • Citations19

A Symmetric Efficient Spatial and Channel Attention (ESCA) Module Based on Convolutional Neural Networks

  • Jul 25, 2024
  • Symmetry
  • Huaiyu Liu +2
  • Conference Article
  • Citations1

Lip-Reading Research Based on ShuffleNet and Attention-GRU

  • Jan 01, 2023
  • AHFE international
  • Yixian Fu +1
  • Research Article
  • Citations197

A CBAM Based Multiscale Transformer Fusion Approach for Remote Sensing Image Change Detection

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Wei Wang +3
  • Research Article
  • Citations1

Novel convolutional neural network architecture with attention mechanisms for real-time in-situ defect detection in metal additive manufacturing

  • Dec 31, 2025
  • Nondestructive Testing and Evaluation
  • S P Maniraj +5
  • Conference Article

Enhancing Convolutional Block Attention with Self-Attention on Agricultural Image Classification

  • Nov 03, 2025
  • Arnab Ghosh Chowdhury +2
  • Research Article

Comparative Study of Baseline and CBAM-Enhanced ResNet50 and MobileNetV2 for Indonesian Rupiah Banknote Classification

  • Jan 04, 2026
  • sinkron
  • Alvin Alvin +2
  • Research Article

An Introspective Study on Attention-Based Transfer Learning in CNNs for Alzheimer's Disease Detection

  • Jan 27, 2025
  • Journal of Information Systems Engineering and Management
  • J Arumugam
  • Research Article
  • Citations1

CSA − HRNet: Channel and Spatial Attention High-Resolution Networks for Semantic Segmentation

  • Dec 10, 2025
  • Journal of Signal Processing Systems
  • Jin-Seong Kim +4
  • Dissertation

Automatic liver tumor segmentation in computed tomography (CT) imaging

  • Jan 01, 2023
  • Kasun Gayashan Hettihewa
  • Research Article
  • Citations7

SST-CRAM: spatial-spectral-temporal based convolutional recurrent neural network with lightweight attention mechanism for EEG emotion recognition.

  • Apr 30, 2024
  • Cognitive neurodynamics
  • Yingxiao Qiao +1
  • Research Article
  • Citations86

A new deep convolutional neural network incorporating attentional mechanisms for ECG emotion recognition

  • Apr 22, 2023
  • Computers in Biology and Medicine
  • Tianqi Fan +8
  • PDF
  • Research Article
  • Citations2

Attention modules in convolutional neural networks for small object recognition

  • Dec 01, 2024
  • Computer Optics
  • D.I Krasnov
  • Research Article
  • Citations3

SCMA: Exploring Dual-Module Attention With Multi-Scale Kernels for Effective Feature Extraction

  • Jan 01, 2023
  • IEEE Access
  • Shaikh Abdus Samad +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.