论文标题
深度学习要看：迈向计算机视觉的新基础
Deep Learning to See: Towards New Foundations of Computer Vision
论文作者
论文摘要
在过去的几年中，计算机视觉的显着进步总的来说，这是由于深度学习的，这是由于大量标记数据的可用性所推动的，并与GPU范式的爆炸性增长搭配。在订阅这一观点的同时，这本书批评了该领域中所谓的科学进步，并在基于信息的自然法则框架内提出了对愿景的调查。具体而言，目前的工作提出了有关视觉的基本问题，这些问题尚未被理解，引导读者走上了一个由新颖挑战引起的与机器学习基础共鸣的旅程。中心论点是，要深入了解视觉计算过程，有必要超越通用机器学习算法的应用，而要专注于考虑视觉信号的时空性质的适当学习理论。
The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal.
