.png){kind=icon}
返回
Explainability-based knowledge distillation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111095.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Knowledge distillation (KD) is a popular approach for deep model acceleration. Based on the knowledge distilled, we categorize KD methods as label-related and structure-related. The former distills the very abstract (high-level) knowledge, e.g., logits; and the latter uses the spatial (low- or medium-level feature) knowledge. However, existing KD methods are usually not explainable, i.e., we do not know what knowledge is transferred during distillation. In this work, we propose a new KD method, Explainability-based Knowledge Distillation (Exp-KD). Specifically, we propose to use class activation map (CAM) as the explainable knowledge which can effectively capture both label- and structure-related information during the distillation. We conduct extensive experiments, including image classification tasks on CIFAR-10, CIFAR-100 and ImageNet datasets, and explainability tests on ImageNet and ImageNet-Segmentation. The results show the great effectiveness and explainability of Exp-KD compared with the state-of-the-art. Code is available at https://github.com/ Blenderama/Exp-KD.
Keyword:
Explainability
Knowledge distillation
CAM
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Reciprocal Teacher-Student Learning via Forward and Feedback Knowledge Distillation通过正向和反馈知识蒸馏实现师生互惠学习
PREAI
分享收藏分享收藏Colorimetric detection of pesticides based on calixarene modified silver nanoparticles in water
PREAI
分享收藏Deep metric learning for few-shot image classification: A Review of recent developments用于少镜头图像分类的深度度量学习: 最新进展综述.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
Oxidative stress in liver of grass carp Ctenopharyngodon idella naturally infected with Saprolegnia parasitica and its influence on disease pathogenesis天然感染水蚤的草鱼肝脏氧化应激及其对疾病发病机制的影响
PREAI
分享收藏
查看更多内容