动态神经网络按输入复杂度调整计算量，提升视觉与多模态融合效率。
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
- 按输出、计算图或输入自适应，实现输入相关计算
- 在嵌入式设备上减少冗余计算，提升部署效率
- 适合多传感器融合场景，支持噪声抑制与信息优先级处理
大模型在嵌入式设备上的部署依赖模型压缩。但传统静态优化方法（如剪枝、量化）忽略不同输入的复杂度差异，导致计算资源浪费。动态神经网络可根据输入特性自适应调整计算量。现有研究广泛且分散，本文系统综述了计算机视觉领域的动态神经网络研究，提出基于网络组件可调性的逻辑分类体系：输出、计算图或输入层面的自适应。进一步指出，动态网络在多模态传感器融合中具有显著优势，可增强适应性、降低噪声并优先处理关键信息，初步展示了相关工作。附带精选论文库，含每篇论文的简要说明与代码链接：https://github.com/DTU-PAS/awesome-dynn-for-cv。
原文摘要 · Abstract (English)
Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different complexities, thus requiring different amount of computations. Dynamic Neural Networks allow to condition the number of computations to the specific input. The current literature on the topic is very extensive and fragmented. We present a comprehensive survey that synthesizes and unifies existing Dynamic Neural Networks research in the context of Computer Vision. Additionally, we provide a logical taxonomy based on which component of the network is adaptive: the output, the computation graph or the input. Furthermore, we argue that Dynamic Neural Networks are particularly beneficial in the context of Sensor Fusion for better adaptivity, noise reduction and information prioritization. We present preliminary works in this direction. We complement this survey with a curated repository listing all the surveyed papers, each with a brief summary of the solution and the code base when available: https://github.com/DTU-PAS/awesome-dynn-for-cv .
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。