深度卷积神经网络量化表示研究 | |
贺翔宇 | |
2022-05 | |
页数 | 132 |
学位类型 | 博士 |
中文摘要 | 量化表示是机器学习领域的一类经典问题,它通过将数据从连续的原空间投影到离散的特征空间,使得计算代价高昂的浮点数乘加操作可以被高效的低数值精度运算替代,从而大幅提升特征向量匹配及以此为基础的相关运算的执行效率。同时,深度卷积神经网络的核心——卷积运算也恰好建立在基于浮点数乘加的相关操作之上,并且卷积层的计算量在深度卷积神经网络总计算量中的占比通常超过90\%。因此,将量化表示引入到深度卷积神经网络的研究中,将为降低深度卷积神经网络的计算复杂度及空间复杂度提供新的思路。 遗憾的是,量化表示在带来计算效率提升的同时,往往也伴随着原始信息的丢失,进而造成模型性能的下降。如何既获取量化表示带来的速度收益,又不过多损失模型表征能力,已经成为深度卷积神经网络量化表示的关键问题。另一方面,对于大量标注数据的依赖性是深度卷积神经网络的另一短板。事实上,用户在期望获得更加轻量化的模型时,并不希望暴露自身的私有数据,这对于已有的基于有标签数据集进行再训练的量化表示算法提出了新的挑战。具体地,深度卷积神经网络量化表示存在如下亟待解决的问题:如何在梯度更新框架下求解量化表示中的离散优化问题、量化表示在小样本/零样本环境下的学习方法应如何设计等。针对以上问题,本文从量化表示学习的角度对深度卷积神经网络模型压缩与加速展开了如下研究: |
英文摘要 | Quantized representation is a long-standing problem in the field of computer vision and the machine learning community, which projects data from a continuous space into a discrete feature space to speed up the following feature matching, retrieval, etc. It replaces the computing-expensive floating-point multiply-add operations with more efficient fixed-point or bitwise operations. Fortunately, the convolution operation, which plays the core role in deep Convolutional Neural Networks (CNN), is also based on floating-point multiply-accumulate operation and consumes over 90\% computing cost in CNN. Therefore, we may solve the problem of high computational and space complexity of CNNs by the quantized representation. Unfortunately, along with the improvements in computational efficiency, quantized representation also suffers from poor performances due to the information loss during the quantization process. We are wondering if it would be possible to enjoy both high efficiency and effectiveness. On the other hand, the dependence on a large amount of labeled data is another shortcoming of deep convolutional neural networks. In fact, the data itself has become more valuable than the model parameters. Both hardware platform suppliers and application developers are expecting more lightweight models. However, due to the user privacy agreements and commercial licenses, they are not allowed to expose the private data and can only provide pre-trained models, which is challenging for the mainstream training-aware quantization schemes. Overall, the quantized representation of deep neural networks becomes more important in real-world applications, still, some crucial issues are rarely discussed, e.g., the discrete optimization problem of the quantized representation under the gradient-based optimization framework, few-shot/one-shot learning methods of quantized representation, differentiable quantization function design, etc. To this end, this dissertation concentrates on the compression and acceleration of deep convolutional neural networks from the perspective of learning-to-quantize. The main contributions are summarized as follows: |
关键词 | 量化表示 特征学习 二值化 深度卷积神经网络 |
语种 | 中文 |
文献类型 | 学位论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48482 |
专题 | 毕业生 |
推荐引用方式 GB/T 7714 | 贺翔宇. 深度卷积神经网络量化表示研究[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
贺翔宇_毕业论文.pdf(10648KB) | 学位论文 | 限制开放 | CC BY-NC-SA |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[贺翔宇]的文章 |
百度学术 |
百度学术中相似的文章 |
[贺翔宇]的文章 |
必应学术 |
必应学术中相似的文章 |
[贺翔宇]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论