.png){kind=icon}
返回
Efficient image classification through collaborative knowledge distillation: A novel AlexNet modification approach
.png){kind=icon}
OA
AI
DOI：10.1016/j.heliyon.2024.e34376.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper introduces an innovative image classification technique utilizing knowledge distillation, tailored for a lightweight model structure. The core of the approach is a modified version of the AlexNet architecture, enhanced with depthwise-separable convolution layers. A unique aspect of this work is the Teacher-Student Collaborative Knowledge Distillation (TSKD) method. Unlike conventional knowledge distillation techniques, TSKD employs a dual-layered learning strategy, where the student model learns from both the final output and the intermediate layers of the teacher model. This collaborative learning approach enables the student model to actively engage in the learning process, resulting in more efficient knowledge transfer. The paper emphasizes the model suitability for scenarios with limited computational resources. This is achieved through architectural optimizations and the introduction of specialized loss functions, which balance the trade-off between model complexity and computational efficiency. The study demonstrates that despite its lightweight nature, the model maintains high accuracy and robustness in image classification tasks. Key contributions of the paper include the innovative use of depthwiseseparable convolution in AlexNet, the TSKD approach for enhanced knowledge transfer, and the development of unique loss functions. These advancements collectively contribute to the model effectiveness in environments with computational constraints, making it a valuable contribution to the field of image classification.
Keyword:
Image classification
Lightweight model
Teacher-student collaborative knowledge
distillation
Modified AlexNet
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
3.8W
被引数:
10.5W
机构
查看更多机构
引用论文
SSD-KD: A self-supervised diverse knowledge distillation method for lightweight skin lesion classification using dermoscopic images.png)
MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏Learning Nonlocal Sparse and Low-Rank Models for Image Compressive Sensing: Nonlocal sparse and low-rank modeling学习非局部稀疏和低秩模型的图像压缩感知: 非局部稀疏和低秩建模
PREAI
分享收藏Joint learning method with teacher-student knowledge distillation for on-device breast cancer image classification面向设备上乳腺癌图像分类的师生知识蒸馏联合学习方法
PREAI
分享收藏Ambiguity-aware robust teacher (ART): Enhance d self-knowle dge distillation framework with pruned teacher networkPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Teacher-student collaborative knowledge distillation for image classification面向图像分类的师生协作知识提炼APPLIED INTELLIGENCEOAAI
APPLIED INTELLIGENCEIF3.5
OAAI分享收藏 没有更多内容