.png){kind=icon}
返回
Goal driven network pruning for object recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2020.107468.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pruning studies up to date focused on uncovering a smaller network by removing redundant units, and fine-tuning to compensate accuracy drop as a result. In this study, unlike the others, we propose an approach to uncover a smaller network that is competent only in a specific task, similar to top-down attention mechanism in human visual system. This approach doesn't require fine-tuning and is proposed as a fast and effective alternative of training from scratch when the network focuses on a specific task in the dataset. Pruning starts from the output and proceeds towards the input by computing neuron importance scores in each layer and propagating them to the preceding layer. In the meantime, neurons determined as worthless are pruned. We applied our approach on three benchmark datasets: MNIST, CIFAR-10 and ImageNet. The results demonstrate that the proposed pruning method typically reduces computational units and storage without harming accuracy significantly. (c) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Deep learning
Computer vision
Network pruning
Network compressing
Top-down attention
Perceptual visioning
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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Saliency for fine-grained object recognition in domains with scarce training data.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
Perceptual modeling in the problem of active object recognition in visual scenesPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容