可学习间距空洞卷积（Dilated Convolution with Learnable Spacings）
Dilated Convolution with Learnable Spacings
AI总结：
本研究提出可学习间距空洞卷积（DCLS）方法，应用于CNN、混合架构及SNN，在视觉、音频多类任务中性能优于现有卷积技术，还实现SNN突触延迟学习并达到SOTA。
摘要：
本论文提出并评估了可学习间距空洞卷积（Dilated Convolution with Learnable Spacings，DCLS）方法。通过在计算机视觉、音频与语音处理领域开展的多项监督学习实验，DCLS方法被证明性能优于标准卷积技术及先进卷积技术。本研究按多个步骤展开，首先在DCLS方法开发前，对相关文献及现有卷积技术进行了分析，我们尤其关注与本方法密切相关的技术，这些技术对于理解我们方法的细微差别与独特性至关重要。本研究的核心是将DCLS方法引入并应用于卷积神经网络（convolutional neural networks, CNNs），以及同时依赖卷积与视觉注意力机制的混合架构中。实验表明，DCLS在分类、语义分割和目标检测等任务中效果尤为突出。本研究最初采用双线性插值，同时也探索了其他插值方法，发现高斯插值可略微提升性能。DCLS方法还被进一步应用于脉冲神经网络（spiking neural networks, SNNs），以在神经网络中实现突触延迟学习，该网络最终可移植到所谓的神经形态芯片上。结果显示，在该领域的某些基准任务中，DCLS方法在SNN音频分类任务上表现突出，成为新的 state-of-the-art 技术，这些任务涉及具有高时间维度成分的数据集。此外，我们证明DCLS可显著提升人工神经网络在多标签音频分类任务中的准确率。最后，我们讨论了所选的实验设置、其局限性、本方法的局限性以及我们的研究结果。
英文摘要：
This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision, audio, and speech processing, the DCLS method proves to outperform both standard and advanced convolution techniques. The research is organized into several steps, starting with an analysis of the literature and existing convolution techniques that preceded the development of the DCLS method. We were particularly interested in the methods that are closely related to our own and that remain essential to capture the nuances and uniqueness of our approach. The cornerstone of our study is the introduction and application of the DCLS method to convolutional neural networks (CNNs), as well as to hybrid architectures that rely on both convolutional and visual attention approaches. DCLS is shown to be particularly effective in tasks such as classification, semantic segmentation, and object detection. Initially using bilinear interpolation, the study also explores other interpolation methods, finding that Gaussian interpolation slightly improves performance. The DCLS method is further applied to spiking neural networks (SNNs) to enable synaptic delay learning within a neural network that could eventually be transferred to so-called neuromorphic chips. The results show that the DCLS method stands out as a new state-of-the-art technique in SNN audio classification for certain benchmark tasks in this field. These tasks involve datasets with a high temporal component. In addition, we show that DCLS can significantly improve the accuracy of artificial neural networks for the multi-label audio classification task. We conclude with a discussion of the chosen experimental setup, its limitations, the limitations of our method, and our results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
