.png){kind=icon}
返回
Foreground separation knowledge distillation for object detection
.png){kind=icon}
OA
AI
DOI：10.7717/peerj-cs.2485.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep learning models have become predominant methods for computer vision tasks, but the large computation and storage requirements of many models make them challenging to deploy on devices with limited resources. Knowledge distillation (KD) is a widely used approach for model compression. However, when applied in the object detection problems, the existing KD methods either directly applies the feature map or simply separate the foreground from the background by using a binary mask, aligning the attention between the teacher and the student models. Unfortunately, these methods either completely overlook or fail to thoroughly eliminate noise, resulting in unsatisfactory model accuracy for student models. To address this issue, we propose a foreground separation distillation (FSD) method in this paper. The FSD method enables student models to distinguish between foreground and background using Gaussian heatmaps, reducing irrelevant information in the learning process. Additionally, FSD also extracts the channel feature by converting the spatial feature maps into probabilistic forms to fully utilize the knowledge in each channel of a well-trained teacher. Experimental results demonstrate that the YOLOX detector enhanced with our distillation method achieved superior performance on both the fall detection and the VOC2007 datasets. For example, YOLOX with FSD achieved 73.1% mean average precision (mAP) on the Fall Detection dataset, which is 1.6% higher than the baseline. The code of FSD is accessible via https://doi.org/10.5281/zenodo.13829676.
Keyword:
Knowledge distillation
Object detection
Foreground separation
Channel feature
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:
2.5
论文数:
3.4K
被引数:
6.9K
机构
引用论文
.png){kind=icon}
Multidimensional Pruning and Its Extension: A Unified Framework for Model Compression多维剪枝及其扩展: 一个统一的模型压缩框架
PREAI
分享收藏Human fall detection on embedded platform using depth maps and wireless accelerometer基于深度图和无线加速度计的嵌入式平台人体跌倒检测
PREAI
分享收藏Adaptive Knowledge Distillation for Lightweight Remote Sensing Object Detectors Optimizing轻量级遥感目标探测器优化的自适应知识蒸馏
PREAI
分享收藏 没有更多内容
没有更多内容