Yi Gong

Yifan Wang, Yi Gong, Yuan Zeng

Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume rendering integral, making it slow to train. Caching NeRFs into explicit data structures can effectively enhance rendering speed but at the cost of higher memory usage. To address these issues, we present Hyb-NeRF, a novel neural radiance field with a multi-resolution hybrid encoding that achieves efficient neural modeling and fast rendering, which also allows for high-quality novel view synthesis. The key idea of Hyb-NeRF is to represent the scene using different encoding strategies from coarse-to-fine resolution levels. Hyb-NeRF exploits memory-efficiency learnable positional features at coarse resolutions and the fast optimization speed and local details of hash-based feature grids at fine resolutions. In addition, to further boost performance, we embed cone tracing-based features in our learnable positional encoding that eliminates encoding ambiguity and reduces aliasing artifacts. Extensive experiments on both synthetic and real-world datasets show that Hyb-NeRF achieves faster rendering speed with better rending quality and even a lower memory footprint in comparison to previous state-of-the-art methods.

Junyong Wang, Yuan Zeng, Yi Gong

Accurate detection of objects in 3D point clouds is a key problem in autonomous driving systems. Collaborative perception can incorporate information from spatially diverse sensors and provide significant benefits for improving the perception accuracy of autonomous driving systems. In this work, we consider that the autonomous vehicle uses local point cloud data and combines information from neighboring infrastructures through wireless links for cooperative 3D object detection. However, information sharing among vehicle and infrastructures in predefined communication schemes may result in communication congestion and/or bring limited performance improvement. To this end, we propose a novel collaborative 3D object detection framework that consists of three components: feature learning networks that map point clouds into feature maps; an efficient communication block that propagates compact and fine-grained query feature maps from vehicle to support infrastructures and optimizes attention weights between query and key to refine support feature maps; a region proposal network that fuses local feature maps and weighted support feature maps for 3D object detection. We evaluate the performance of the proposed framework using a synthetic cooperative dataset created in two complex driving scenarios: a roundabout and a T-junction. Experiment results and bandwidth usage analysis demonstrate that our approach can save communication and computation costs and significantly improve detection performance under different detection difficulties in all scenarios.

Xiang Zhou, Yuan Zeng, Yi Gong

Recent advances in deep generative adversarial networks (GAN) and self-attention mechanism have led to significant improvements in the challenging task of inpainting large missing regions in an image. These methods integrate self-attention mechanism in neural networks to utilize surrounding neural elements based on their correlation and help the networks capture long-range dependencies. Temperature is a parameter in the Softmax function used in the self-attention, and it enables biasing the distribution of attention scores towards a handful of similar patches. Most existing self-attention mechanisms in image inpainting are convolution-based and set the temperature as a constant, performing patch matching in a limited feature space. In this work, we analyze the artifacts and training problems in previous self-attention mechanisms, and redesign the temperature learning network as well as the self-attention mechanism to address them. We present an image inpainting framework with a multi-head temperature masked self-attention mechanism, which provides stable and efficient temperature learning and uses multiple distant contextual information for high quality image inpainting. In addition to improving image quality of inpainting results, we generalize the proposed model to user-guided image editing by introducing a new sketch generation method. Extensive experiments on various datasets such as Paris StreetView, CelebA-HQ and Places2 clearly demonstrate that our method not only generates more natural inpainting results than previous works both in terms of perception image quality and quantitative metrics, but also enables to help users to generate more flexible results that are related to their sketch guidance.

Shangao Lin, Yuan Zeng, Yi Gong

Recent learning-based image classification and speech recognition approaches make extensive use of attention mechanisms to achieve state-of-the-art recognition power, which demonstrates the effectiveness of attention mechanisms. Motivated by the fact that the frequency and time information of modulated radio signals are crucial for modulation mode recognition, this paper proposes a time-frequency attention mechanism for a convolutional neural network (CNN)-based modulation recognition framework. The proposed time-frequency attention module is designed to learn which channel, frequency and time information is more meaningful in CNN for modulation recognition. We analyze the effectiveness of the proposed time-frequency attention mechanism and compare the proposed method with two existing learning-based methods. Experiments on an open-source modulation recognition dataset show that the recognition performance of the proposed framework is better than those of the framework without time-frequency attention and existing learning-based methods.

Yi Gong, Xinyuan Zhang, Jichen Chai et al.

Cardiac contraction is a rapid, coordinated process that unfolds across three-dimensional tissue on millisecond timescales. Traditional optical imaging is often inadequate for capturing dynamic cellular structure in the beating heart because of a fundamental trade-off between spatial and temporal resolution. To overcome these limitations, we propose a high-performance computational imaging framework that integrates Compressive Sensing (CS) with Light-Sheet Microscopy (LSM) for efficient, low-phototoxic cardiac imaging. The system performs compressed acquisition of fluorescence signals via random binary mask coding using a Digital Micromirror Device (DMD). We propose a Plug-and-Play (PnP) framework, solved using the alternating direction method of multipliers (ADMM), which flexibly incorporates advanced denoisers, including Tikhonov, Total Variation (TV), and BM3D. To preserve structural continuity in dynamic imaging, we further introduce temporal regularization enforcing smoothness between adjacent z-slices. Experimental results on zebrafish heart imaging under high compression ratios demonstrate that the proposed method successfully reconstructs cellular structures with excellent denoising performance and image clarity, validating the effectiveness and robustness of our algorithm in real-world high-speed, low-light biological imaging scenarios.

Zhenrong Liu, Yang Li, Yi Gong et al.

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.

Mingzhi Jiang, Tianhao Wu, Zhe Wang et al.

Cooperative Intelligent Transportation Systems (C-ITS) will change the modes of road safety and traffic management, especially at intersections without traffic lights, namely unsignalized intersections. Existing researches focus on vehicle control within a small area around an unsignalized intersection. In this paper, we expand the control domain to a large area with multiple intersections. In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections. Firstly, a vehicular end-edge-cloud computing framework is proposed to facilitate end-edge-cloud vertical cooperation and horizontal cooperation among vehicles. Then, the vehicular cooperative control problems in the cloud and edge layers are formulated as Markov Decision Process (MDP) and solved by two-stage reinforcement learning. Furthermore, to deal with high-density traffic, vehicle selection methods are proposed to reduce the state space and accelerate algorithm convergence without performance degradation. A multi-intersection simulation platform is developed to evaluate the proposed scheme. Simulation results show that the proposed MiVeCC can improve travel efficiency at multiple intersections by up to 4.59 times without collision compared with existing methods.

Weiheng Jiang, Xiaogang Wu, Yi Gong et al.

The electricity consumption forecasting is a critical component of the intelligent power system. And accurate monthly electricity consumption forecasting, as one of the the medium and long term electricity consumption forecasting problems, plays an important role in dispatching and management for electric power systems. Although there are many studies for this problem, large sample data set is generally required to obtain higher prediction accuracy, and the prediction performance become worse when only a little data is available. However, in practical, mostly we experience the problem of insufficient sample data and how to accurately forecast the monthly electricity consumption with limited sample data is a challenge task. The Holt-Winters exponential smoothing method often used to forecast periodic series due to low demand for training data and high accuracy for forecasting. In this paper, based on Holt-Winters exponential smoothing method, we propose a hybrid forecasting model named FOA-MHW. The main idea is that, we use fruit fly optimization algorithm to select smoothing parameters for Holt-Winters exponential smoothing method. Besides, electricity consumption data of a city in China is used to comprehensively evaluate the forecasting performance of the proposed model. The results indicate that our model can significantly improve the accuracy of monthly electricity consumption forecasting even in the case that only a small number of training data is available.

Xin He, Meng Sun, Wee Peng Tay et al.

A sensor network wishes to transmit information to a fusion center to allow it to detect a public hypothesis, but at the same time prevent it from inferring a private hypothesis. We propose a multilayer nonlinear processing procedure at each sensor to distort the sensor's data before it is sent to the fusion center. In our proposed framework, sensors are grouped into clusters, and each sensor first applies a nonlinear fusion function on the information it receives from sensors in the same cluster and in a previous layer. A linear weighting matrix is then used to distort the information it sends to sensors in the next layer. We adopt a nonparametric approach and develop a modified mirror descent algorithm to optimize the weighting matrices so as to ensure that the regularized empirical risk of detecting the private hypothesis is above a given privacy threshold, while minimizing the regularized empirical risk of detecting the public hypothesis. Experiments on empirical datasets demonstrate that our approach is able to achieve a good trade-off between the error rates of the public and private hypothesis.