No abstract

No abstract

Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to different inputs, leading to notable advantages in terms of accuracy, computational efficiency, adaptiveness, etc. In this survey, we comprehensively review this rapidly developing area by dividing dynamic networks into three main categories: 1) instance-wise dynamic models that process each instance with data-dependent architectures or parameters; 2) spatial-wise dynamic networks that conduct adaptive computation with respect to different spatial locations of image data and 3) temporal-wise dynamic models that perform adaptive inference along the temporal dimension for sequential data such as videos and texts. The important research problems of dynamic networks, e.g., architecture design, decision making scheme, optimization technique and applications, are reviewed systematically. Finally, we discuss the open problems in this field together with interesting future research directions.

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions. Then the selected patches are inferred by a highcapacity network for the final prediction. During offline inference, once the informative patch sequence has been generated, the bulk of computation can be done in parallel, and is efficient on modern GPU devices. In addition, we demonstrate that the proposed method can be easily extended by further considering the temporal redundancy, e.g., dynamically skipping less valuable frames. Extensive experiments on five benchmark datasets, i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, demonstrate that our method is significantly more efficient than the competitive baselines. Code will be available at https:// github.com/blackfeather-wang/AdaFocus.

No abstract

No abstract

No abstract

It has been recently shown that a solid-textured metal cylinder can support electric and magnetic dipolar resonances simultaneously [Phys. Rev. X4, 021003 (2014)PRXHAE2160-330810.1103/PhysRevX.4.021003] which are almost degenerate in a two-dimensional (2-D) structure and non-degenerate in a three-dimensional (3-D) structure, and with the magnetic dipole appearing at higher frequency. They are described as spoof localized plasmonic modes analogous to localized plasmonic resonances in optical frequencies. Here, we consider a hollow metal cylinder corrugated by periodic cut-through slits. Our results indicate that the magnetic dipole can be separated from the electric dipole in a 2-D structure, and magnetic dipolar resonance appears at lower frequency, rather than electric resonance in both 2-D and 3-D structures. In order to clarify the physical mechanism behind the abnormal phenomenon, we study the influence of the core material on the electric- and magnetic-dipole modes based on theoretical analysis and numerical simulation. It is discovered that there is a threshold of an imaginary part of permittivity for switching the order between electric and magnetic dipoles. These results may provide fundamental understanding and physical insight for spoof plasmonic modes supported in designer structures.