Related papers: DRIFT-Net: A Spectral--Coupled Neural Operator for…
Partial differential equations (PDEs) are commonly derived based on empirical observations. However, recent advances of technology enable us to collect and store massive amount of data, which offers new opportunities for data-driven…
Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This…
Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different…
Neural networks have been applied to control problems, typically by combining data, differential equation residuals, and objective costs in the training loss or by incorporating auxiliary architectural components. Instead, we propose a…
Massively parallel systolic arrays and resource-efficient depthwise separable convolutions are two promising techniques to accelerate DNN inference on the edge. Interestingly, their combination is inefficient: Computational patterns of…
We present a data-driven framework that extends the predictive capability of classical lifting-line theory (LLT) to a wider aerodynamic regime by incorporating higher-fidelity aerodynamic data from panel method simulations. A neural network…
The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational…
Uncertainty and delayed reactions in human driving behavior lead to stop-and-go traffic congestion on freeways. The freeway traffic dynamics are governed by the Aw-Rascle-Zhang (ARZ) traffic Partial Differential Equation (PDE) models with…
The neural operator has emerged as a powerful tool in learning mappings between function spaces in PDEs. However, when faced with real-world physical data, which are often highly non-uniformly distributed, it is challenging to use…
A neural network is essentially a high-dimensional complex mapping model by adjusting network weights for feature fitting. However, the spectral bias in network training leads to unbearable training epochs for fitting the high-frequency…
We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mean-field theory (DMFT) that jointly tracks bulk and outlier spectral dynamics for spiked…
Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two mainstream methods.…
Parametric PDEs power modern simulation, design, and digital-twin systems, yet their many-query workloads still hinge on repeatedly solving large finite-element systems. Existing operator-learning approaches accelerate this process but…
Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uniform mapping tailored to average dataset distributions, leading to over-processing…
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and…
Accurately modeling and forecasting complex systems governed by partial differential equations (PDEs) is crucial in various scientific and engineering domains. However, traditional numerical methods struggle in real-world scenarios due to…
Recently, spiking neural networks (SNNs) have demonstrated substantial potential in computer vision tasks. In this paper, we present an Efficient Spiking Deraining Network, called ESDNet. Our work is motivated by the observation that rain…
Spectral image reconstruction is an important task in snapshot compressed imaging. This paper aims to propose a new end-to-end framework with iterative capabilities similar to a deep unfolding network to improve reconstruction accuracy,…
Traditional approaches to stabilizing hyperbolic PDEs, such as PDE backstepping, often encounter challenges when dealing with high-dimensional or complex nonlinear problems. Their solutions require high computational and analytical costs.…
Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with…