.png){kind=icon}
返回
Cross-model temporal cooperation via saliency maps for efficient frame classification
.png){kind=icon}
PRE
AI
DOI：10.1109/ICCVW60793.2023.00125.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Minimizing the energy consumption of deep learning models is becoming essential due to the increasing pervasiveness of connected and mobile devices. Real-time video frame classification is a perfect example of energy-intensive task that could present battery consumption and overheating issues on embedded devices. In this paper we propose a novel architecture to tackle this problem efficiently, exploiting temporal redundancies between consecutive frames. The model consists of two convolutional neural network streams with different parameter sizes and input resolutions. Each frame is processed by only one of the streams, and the stream with the lowest input resolution and parameter size uses saliency maps generated by the other stream on a previous frame. The energy consumption can be manually controlled by choosing a proper schedule of the two streams. We show the effectiveness of our proposed architecture in a task that involves recognizing the state of the relevant traffic lights in images from on-board cameras.
期刊
机构
引用论文
分享收藏Attention gated networks: Learning to leverage salient regions in medical images注意门控网络: 学习利用医学图像中的显着区域.png)
MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏Impact of Coronavirus Disease-19 Lockdown on Egyptian Children and Adolescents: Dietary Pattern Changes Health Risk冠状病毒疾病-19封锁对埃及儿童和青少年的影响: 饮食模式改变健康风险
OAAI
OAAI分享收藏 没有更多内容
没有更多内容