Optimizing Waste Management with Squeeze-and-Excitation and Convolutional Block Attention Integration in ResNet-Based Deep Learning Frameworks

Saiprasad Potharaju; Swapnali N Tambe; Satya Kiranmai Tadepalli; Shobarani Salvadi; T.C.Manjunath; A. Srilakshmi

doi:10.37965/jait.2025.0709

Optimizing Waste Management with Squeeze-and-Excitation and Convolutional Block Attention Integration in ResNet-Based Deep Learning Frameworks

Authors

Saiprasad Potharaju Department of CSE, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India
Swapnali N Tambe Department of Information Technology, K. K.Wagh Institute of Engineering Education & Research, Nashik, MH, India
Satya Kiranmai Tadepalli Chaitanya Bharathi Institute of Technology(A), Hyderabad, Telangana, India
Shobarani Salvadi Chaitanya Bharathi Institute of Technology(A), Hyderabad, Telangana, India
T.C.Manjunath Department of Computer Science & Engineering, RajaRajeswari College of Engineering, Bengaluru, Karnataka, India https://orcid.org/0000-0003-2545-9160
A. Srilakshmi Department of IT, Chaitanya Bharathi Institute of Technology(A), Hyderabad, Telangana, India

DOI:

https://doi.org/10.37965/jait.2025.0709

Keywords:

deep learning, attention mechanism, automated waste classification, squeeze-and-excitation (SE), convolutional block attention module (CBAM)

Abstract

Effective waste classification is crucial for sustainable waste management, yet existing automated models face challenges such as misclassification of visually similar waste materials, dataset imbalance, and poor generalization to real-world conditions. This study addresses these limitations by integrating Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) mechanisms into ResNet-50, a deep learning model, to improve waste classification accuracy. Utilizing the TrashNet dataset (six waste categories), we have employed the Synthetic Minority Over-sampling Technique (SMOTE) to balance the dataset, increasing samples from 2,527 to 3,564. Experimental results demonstrate significant improvements: ResNet-50 achieves 74.42% test accuracy, SE+ResNet-50 improves accuracy to 93.47%, and CBAM+ResNet-50 reaches 95.74%. The findings highlight that attention-based deep learning models can significantly enhance feature extraction, improve classification accuracy, and optimize waste segregation processes, contributing to more efficient recycling and waste management automation. Future work includes extending the model to classify hazardous and mixed waste, ensuring broader applicability in real-world waste management systems.