Related papers: Diffractive Magic Cube Network with Super-high Cap…
Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices. In this paper, we…
Traffic prediction is a critical component of intelligent transportation systems, enabling applications such as congestion mitigation and accident risk prediction. While recent research has explored both graph-based and grid-based…
A cascaded phase-only mask architecture (or an optical diffractive neural network) can be employed for different optical information processing tasks such as pattern recognition, orbital angular momentum (OAM) mode conversion, image…
Emerging reconfigurable datacenters allow to dynamically adjust the network topology in a demand-aware manner. These datacenters rely on optical switches which can be reconfigured to provide direct connectivity between racks, in the form of…
Deep Neural Networks (DNNs) approaches for the Optimal Power Flow (OPF) problem received considerable attention recently. A key challenge of these approaches lies in ensuring the feasibility of the predicted solutions to physical system…
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…
We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1.…
Resource allocation remains NP-hard due to combinatorial complexity. While deep reinforcement learning (DRL) methods, such as the Rainbow Deep Q-Network (DQN), improve scalability through prioritized replay and distributional heads,…
The conjugation of multiple spatial light modulators (SLMs) enables the construction of optical diffractive neural networks (DNNs). To accelerate training, which is limited by the low refresh rate of SLMs, spatial multiplexing of the input…
The most recent deep neural network (DNN) models exhibit impressive denoising performance in the time-frequency (T-F) magnitude domain. However, the phase is also a critical component of the speech signal that is easily overlooked. In this…
Data center networks (DCNs) are essential infrastructures to embrace the era of highly diversified massive amount of data generated by emerging technological applications. In order to store and process such a data deluge, today's DCNs have…
Constellation shaping is a practical and effective technique to improve the performance and the rate adaptivity of optical communication systems. In principle, it could also be used to mitigate the impact of nonlinear effects, possibly…
We report a broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally-incoherent broadband source to all-optically perform a specific task learned using deep…
Convolutional neural networks (CNNs) have shown great effectiveness in medical image segmentation. However, they may be limited in modeling large inter-subject variations in organ shapes and sizes and exploiting global long-range contextual…
We report a monochrome multi-task diffractive network architecture that leverages illumination phase multiplexing to dynamically reconfigure its output function and accurately implement a large group of complex-valued linear transformations…
The redundancy of Convolutional neural networks not only depends on weights but also depends on inputs. Shuffling is an efficient operation for mixing channel information but the shuffle order is usually pre-defined. To reduce the…
Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attention limit performance in dynamic scenes with occlusions,…
Deep neural networks with more parameters and FLOPs have higher capacity and generalize better to diverse domains. But to be deployed on edge devices, the model's complexity has to be constrained due to limited compute resource. In this…
We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN). It applies given spatial transformations directly to a…
In this paper we propose and investigate the performance of a multi-channel scheduling algorithm based on the well-known deficit round-robin (DRR), which we call multi-channel DRR (MCDRR). We extend the original DRR to the case of multiple…