通过批归一化层压缩深度网络，降低计算开销。
Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers
- 从批归一化层视角出发，动态剪裁网络深度。
- 在Swin-T、MobileNet-V2等模型上实现显著压缩率。
- 适用于图像分类与NLP任务，适合资源受限场景。
当前深度神经网络因其通用性被广泛应用于各类复杂任务，但通常存在参数过多的问题，导致计算资源消耗大。本文提出一种名为Till the Layers Collapse（TLC）的方法，通过分析批归一化层的特性来压缩深层网络，减少模型深度以降低计算需求和延迟。该方法在Swin-T、MobileNet-V2和RoBERTa等主流模型上进行了验证，涵盖图像分类与自然语言处理任务，有效提升了模型效率。
原文摘要 · Abstract (English)
Today, deep neural networks are widely used since they can handle a variety of complex tasks. Their generality makes them very powerful tools in modern technology. However, deep neural networks are often overparameterized. The usage of these large models consumes a lot of computation resources. In this paper, we introduce a method called \textbf{T}ill the \textbf{L}ayers \textbf{C}ollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers. By reducing the depth of these networks, our method decreases deep neural networks' computational requirements and overall latency. We validate our method on popular models such as Swin-T, MobileNet-V2, and RoBERTa, across both image classification and natural language processing (NLP) tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。