arXiv subjects

Yi Huang

Publications and source records attributed to Yi Huang.

At least 145 records · Page 8Linked to original sources

arXiv2023

MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings

Although the majority of recent autonomous driving systems concentrate on developing perception methods based on ego-vehicle sensors, there is an overlooked alternative approach that involves leveraging intelligent roadside cameras to help extend the ego-vehicle perception ability beyond the visual range. We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground. However, the roadside camera is installed on a pole with a pitched angle, which makes the existing methods not optimal for roadside scenes. In this paper, we introduce a novel framework for Roadside Monocular 3D object detection with ground-aware embeddings, named MonoGAE. Specifically, the ground plane is a stable and strong prior knowledge due to the fixed installation of cameras in roadside scenarios. In order to reduce the domain gap between the ground geometry information and high-dimensional image features, we employ a supervised training paradigm with a ground plane to predict high-dimensional ground-aware embeddings. These embeddings are subsequently integrated with image features through cross-attention mechanisms. Furthermore, to improve the detector's robustness to the divergences in cameras' installation poses, we replace the ground plane depth map with a novel pixel-level refined ground plane equation map. Our approach demonstrates a substantial performance advantage over all previous monocular 3D object detectors on widely recognized 3D detection benchmarks for roadside cameras. The code and pre-trained models will be released soon.

cs.CV↗

arXiv2023

BEVHeight++: Toward Robust Visual Centric 3D Object Detection

While most recent autonomous driving system focuses on developing perception methods on ego-vehicle sensors, people tend to overlook an alternative approach to leverage intelligent roadside cameras to extend the perception ability beyond the visual range. We discover that the state-of-the-art vision-centric bird's eye view detection methods have inferior performances on roadside cameras. This is because these methods mainly focus on recovering the depth regarding the camera center, where the depth difference between the car and the ground quickly shrinks while the distance increases. In this paper, we propose a simple yet effective approach, dubbed BEVHeight++, to address this issue. In essence, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods. By incorporating both height and depth encoding techniques, we achieve a more accurate and robust projection from 2D to BEV spaces. On popular 3D detection benchmarks of roadside cameras, our method surpasses all previous vision-centric methods by a significant margin. In terms of the ego-vehicle scenario, our BEVHeight++ possesses superior over depth-only methods. Specifically, it yields a notable improvement of +1.9% NDS and +1.1% mAP over BEVDepth when evaluated on the nuScenes validation set. Moreover, on the nuScenes test set, our method achieves substantial advancements, with an increase of +2.8% NDS and +1.7% mAP, respectively.

cs.CV↗

arXiv2023

UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation

An unpaired image-to-image (I2I) translation technique seeks to find a mapping between two domains of data in a fully unsupervised manner. While initial solutions to the I2I problem were provided by generative adversarial neural networks (GANs), diffusion models (DMs) currently hold the state-of-the-art status on the I2I translation benchmarks in terms of Frechet inception distance (FID). Yet, DMs suffer from limitations, such as not using data from the source domain during the training or maintaining consistency of the source and translated images only via simple pixel-wise errors. This work improves a recent UVCGAN model and equips it with modern advancements in model architectures and training procedures. The resulting revised model significantly outperforms other advanced GAN- and DM-based competitors on a variety of benchmarks. In the case of Male-to-Female translation of CelebA, the model achieves more than 40% improvement in FID score compared to the state-of-the-art results. This work also demonstrates the ineffectiveness of the pixel-wise I2I translation faithfulness metrics and suggests their revision. The code and trained models are available at https://github.com/LS4GAN/uvcgan2

cs.CV↗

arXiv2023

Graph Edit Distance Learning via Different Attention

Recently, more and more research has focused on using Graph Neural Networks (GNN) to solve the Graph Similarity Computation problem (GSC), i.e., computing the Graph Edit Distance (GED) between two graphs. These methods treat GSC as an end-to-end learnable task, and the core of their architecture is the feature fusion modules to interact with the features of two graphs. Existing methods consider that graph-level embedding is difficult to capture the differences in local small structures between two graphs, and thus perform fine-grained feature fusion on node-level embedding can improve the accuracy, but leads to greater time and memory consumption in the training and inference phases. However, this paper proposes a novel graph-level fusion module Different Attention (DiffAtt), and demonstrates that graph-level fusion embeddings can substantially outperform these complex node-level fusion embeddings. We posit that the relative difference structure of the two graphs plays an important role in calculating their GED values. To this end, DiffAtt uses the difference between two graph-level embeddings as an attentional mechanism to capture the graph structural difference of the two graphs. Based on DiffAtt, a new GSC method, named Graph Edit Distance Learning via Different Attention (REDRAFT), is proposed, and experimental results demonstrate that REDRAFT achieves state-of-the-art performance in 23 out of 25 metrics in five benchmark datasets. Especially on MSE, it respectively outperforms the second best by 19.9%, 48.8%, 29.1%, 31.6%, and 2.2%. Moreover, we propose a quantitative test Remaining Subgraph Alignment Test (RESAT) to verify that among all graph-level fusion modules, the fusion embedding generated by DiffAtt can best capture the structural differences between two graphs.

cs.AI↗

arXiv2023

Designing a Deep Learning-Driven Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries

Breast cancer is one of the leading causes of cancer mortality. Breast cancer patients in developing countries, especially sub-Saharan Africa, South Asia, and South America, suffer from the highest mortality rate in the world. One crucial factor contributing to the global disparity in mortality rate is long delay of diagnosis due to a severe shortage of trained pathologists, which consequently has led to a large proportion of late-stage presentation at diagnosis. The delay between the initial development of symptoms and the receipt of a diagnosis could stretch upwards 15 months. To tackle this critical healthcare disparity, this research has developed a deep learning-based diagnosis system for metastatic breast cancer that can achieve high diagnostic accuracy as well as computational efficiency. Based on our evaluation, the MobileNetV2-based diagnostic model outperformed the more complex VGG16, ResNet50 and ResNet101 models in diagnostic accuracy, model generalization, and model training efficiency. The visual comparisons between the model prediction and ground truth have demonstrated that the MobileNetV2 diagnostic models can identify very small cancerous nodes embedded in a large area of normal cells which is challenging for manual image analysis. Equally Important, the light weighted MobleNetV2 models were computationally efficient and ready for mobile devices or devices of low computational power. These advances empower the development of a resource-efficient and high performing AI-based metastatic breast cancer diagnostic system that can adapt to under-resourced healthcare facilities in developing countries. This research provides an innovative technological solution to address the long delays in metastatic breast cancer diagnosis and the consequent disparity in patient survival outcome in developing countries.

eess.IV↗

arXiv2023

High-fidelity achromatic metalens imaging via deep neural network

Meta-optics are attracting intensive interest as alternatives to traditional optical systems comprising multiple lenses and diffractive elements. Among applications, single metalens imaging is highly attractive due to the potential for achieving significant size reduction and simplified design. However, single metalenses exhibit severe chromatic aberration arising from material dispersion and the nature of singlet optics, making them unsuitable for full-color imaging requiring achromatic performance. In this work, we propose and validate a deep learning-based single metalens imaging system to overcome chromatic aberration in varied scenarios. The developed deep learning networks computationally reconstruct raw imaging captures through reliably refocusing red, green and blue channels to eliminate chromatic aberration and enhance resolution without altering the metalens hardware. The networks demonstrate consistent enhancement across different aperture sizes and focusing distances. Images outside the training set and real-world photos were also successfully reconstructed. Our approach provides a new means to achieve achromatic metalenses without complex engineering, enabling practical and simplified implementation to overcome inherent limitations of meta-optics.

physics.optics↗

arXiv2023

A Unified Distributed Method for Constrained Networked Optimization via Saddle-Point Dynamics

This paper develops a unified distributed method for solving two classes of constrained networked optimization problems, i.e., optimal consensus problem and resource allocation problem with non-identical set constraints. We first transform these two constrained networked optimization problems into a unified saddle-point problem framework with set constraints. Subsequently, two projection-based primal-dual algorithms via Optimistic Gradient Descent Ascent (OGDA) method and Extra-gradient (EG) method are developed for solving constrained saddle-point problems. It is shown that the developed algorithms achieve exact convergence to a saddle point with an ergodic convergence rate $O(1/k)$ for general convex-concave functions. Based on the proposed primal-dual algorithms via saddle-point dynamics, we develop unified distributed algorithm design and convergence analysis for these two networked optimization problems. Finally, two numerical examples are presented to demonstrate the theoretical results.

math.OC↗

arXiv2023

Integrating Different Informations for Portfolio Selection

Following the idea of Bayesian learning via Gaussian mixture model, we organically combine the backward-looking information contained in the historical data and the forward-looking information implied by the market portfolio, which is affected by heterogeneous expectations and noisy trading behavior. The proposed combined estimation adaptively harmonizes these two types of information based on the degree of market efficiency and responds quickly at turning points of the market. Both simulation experiments and a global empirical test confirm that the approach is a flexible and robust forecasting tool and is applicable to various capital markets with different degrees of efficiency.

q-fin.PM↗

arXiv2023

Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision

Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses. In real-life applications, user utterances are noisier, and thus it is more difficult to accurately track dialog states and correctly secure relevant knowledge. Recently, a progress in question answering and document-grounded dialog systems is retrieval-augmented methods with a knowledge retriever. Inspired by such progress, we propose a retrieval-based method to enhance knowledge selection in TOD systems, which significantly outperforms the traditional database query method for real-life dialogs. Further, we develop latent variable model based semi-supervised learning, which can work with the knowledge retriever to leverage both labeled and unlabeled dialog data. Joint Stochastic Approximation (JSA) algorithm is employed for semi-supervised model training, and the whole system is referred to as that JSA-KRTOD. Experiments are conducted on a real-life dataset from China Mobile Custom-Service, called MobileCS, and show that JSA-KRTOD achieves superior performances in both labeled-only and semi-supervised settings.

cs.CL↗

arXiv2023

Learning Higher-order Object Interactions for Keypoint-based Video Understanding

Action recognition is an important problem that requires identifying actions in video by learning complex interactions across scene actors and objects. However, modern deep-learning based networks often require significant computation, and may capture scene context using various modalities that further increases compute costs. Efficient methods such as those used for AR/VR often only use human-keypoint information but suffer from a loss of scene context that hurts accuracy. In this paper, we describe an action-localization method, KeyNet, that uses only the keypoint data for tracking and action recognition. Specifically, KeyNet introduces the use of object based keypoint information to capture context in the scene. Our method illustrates how to build a structured intermediate representation that allows modeling higher-order interactions in the scene from object and human keypoints without using any RGB information. We find that KeyNet is able to track and classify human actions at just 5 FPS. More importantly, we demonstrate that object keypoints can be modeled to recover any loss in context from using keypoint information over AVA action and Kinetics datasets.

cs.CV↗

arXiv2023

Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains

Images taken under low-light conditions tend to suffer from poor visibility, which can decrease image quality and even reduce the performance of the downstream tasks. It is hard for a CNN-based method to learn generalized features that can recover normal images from the ones under various unknow low-light conditions. In this paper, we propose to incorporate the contrastive learning into an illumination correction network to learn abstract representations to distinguish various low-light conditions in the representation space, with the purpose of enhancing the generalizability of the network. Considering that light conditions can change the frequency components of the images, the representations are learned and compared in both spatial and frequency domains to make full advantage of the contrastive learning. The proposed method is evaluated on LOL and LOL-V2 datasets, the results show that the proposed method achieves better qualitative and quantitative results compared with other state-of-the-arts.

cs.CV↗

arXiv2023

Usability of Privacy Controls in Top Health Websites

With the increasing awareness and concerns around privacy, many service providers offer their users various privacy controls. Through these controls, users gain greater authority over the collection, utilisation, and dissemination of their personal information by the services. However, these controls may be buried deep within menus or settings, making them difficult for a user to access. Additionally, the terminology used to describe privacy controls can sometimes be confusing or technical, further complicating the user's ability to understand and use them effectively. This is especially true for health websites, as users often share sensitive information about their health and well-being. While many privacy controls have been proposed to protect user data on these sites, existing research focuses on individual controls (e.g., privacy policies or cookie opt-outs) rather than providing a comprehensive overview of the privacy landscape. In addition, many studies concentrate on the technical aspects of privacy controls without considering the usability of these features from a user's perspective. This paper aims to fill the gaps in the existing work by analysing four privacy controls, namely privacy nudge, privacy notice, privacy policy, and privacy setting, and evaluating their usability on the top 100 most visited health websites. First, we define usability attributes for each privacy control in three website visit scenarios; the guest, registering, and log-in visits. These attributes include awareness, efficiency, comprehension, functionality, and choice. Then, we design a survey template based on these attributes and scenarios and collect data about privacy controls. Next, we analyse the availability and usability of each privacy control on health websites. Finally, we provide suggestions for improving the design of these privacy controls based on the data analysis results.

cs.CR↗

arXiv2023

Multi-Action Dialog Policy Learning from Logged User Feedback

Multi-action dialog policy, which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing policy models usually imitate action combinations from the labeled multi-action dialog examples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid objective of semi-supervised learning and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch outperforms the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

cs.CL↗

arXiv2023

A holistically 3D-printed flexible millimeter-wave Doppler radar: Towards fully printed high-frequency multilayer flexible hybrid electronics systems

Flexible hybrid electronics (FHE) is an emerging technology enabled through the integration of advanced semiconductor devices and 3D printing technology. It unlocks tremendous market potential by realizing low-cost flexible circuits and systems that can be conformally integrated into various applications. However, the operating frequencies of most reported FHE systems are relatively low. It is also worth to note that reported FHE systems have been limited to relatively simple design concept (since complex systems will impose challenges in aspects such as multilayer interconnections, printing materials, and bonding layers). Here, we report a fully 3D-printed flexible four-layer millimeter-wave Doppler radar (i.e., a millimeter-wave FHE system). The sensing performance and flexibility of the 3D-printed radar are characterized and validated by general field tests and bending tests, respectively. Our results demonstrate the feasibility of developing fully 3D-printed high-frequency multilayer FHE, which can be conformally integrated into irregular surfaces (e.g., vehicle bumpers) for applications such as vehicle radars and wearable electronics.

eess.SY↗

arXiv2023

Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems

Recently, two approaches, fine-tuning large pre-trained language models and variational training, have attracted significant interests, separately, for semi-supervised end-to-end task-oriented dialog (TOD) systems. In this paper, we propose Variational Latent-State GPT model (VLS-GPT), which is the first to combine the strengths of the two approaches. Among many options of models, we propose the generative model and the inference model for variational learning of the end-to-end TOD system, both as auto-regressive language models based on GPT-2, which can be further trained over a mix of labeled and unlabeled dialog data in a semi-supervised manner. Variational training of VLS-GPT is both statistically and computationally more challenging than previous variational learning works for sequential latent variable models, which use turn-level first-order Markovian. The inference model in VLS-GPT is non-Markovian due to the use of the Transformer architecture. In this work, we establish Recursive Monte Carlo Approximation (RMCA) to the variational objective with non-Markovian inference model and prove its unbiasedness. Further, we develop the computational strategy of sampling-then-forward-computation to realize RMCA, which successfully overcomes the memory explosion issue of using GPT in variational learning and speeds up training. Semi-supervised TOD experiments are conducted on two benchmark multi-domain datasets of different languages - MultiWOZ2.1 and CrossWOZ. VLS-GPT is shown to significantly outperform both supervised-only and semi-supervised self-training baselines.

cs.CL↗

arXiv2022

Distributed Event-Triggered Algorithm for Convex Optimization with Coupled Constraints

This paper develops a distributed primal-dual algorithm via event-triggered mechanism to solve a class of convex optimization problems subject to local set constraints, coupled equality and inequality constraints. Different from some existing distributed algorithms with the diminishing step-sizes, our algorithm uses the constant step-sizes, and is shown to achieve an exact convergence to an optimal solution with an $O(1/k)$ convergence rate for general convex objective functions, where $k>0$ is the iteration number. Moreover, by applying event-triggered communication mechanism, the proposed algorithm can effectively reduce the communication cost without sacrificing the convergence rate. Finally, a numerical example is presented to verify the effectiveness of the proposed algorithm.

math.OC↗

arXiv2022

UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-consistency constraint. To achieve this, we equip the generator with a Vision Transformer (ViT) and employ necessary training and regularization techniques. Compared to previous best-performing models, our model performs better and retains a strong correlation between the original and translated image. An accompanying ablation study shows that both the gradient penalty and self-supervised pre-training are crucial to the improvement. To promote reproducibility and open science, the source code, hyperparameter configurations, and pre-trained model are available at https://github.com/LS4GAN/uvcgan.

cs.CV↗

arXiv2022

Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Dataset

Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games. However, the Wizard-of-Oz data are in fact simulated data and thus are fundamentally different from real-life conversations, which are more noisy and casual. Recently, the SereTOD challenge is organized and releases the MobileCS dataset, which consists of real-world dialog transcripts between real users and customer-service staffs from China Mobile. Based on the MobileCS dataset, the SereTOD challenge has two tasks, not only evaluating the construction of the dialogue system itself, but also examining information extraction from dialog transcripts, which is crucial for building the knowledge base for TOD. This paper mainly presents a baseline study of the two tasks with the MobileCS dataset. We introduce how the two baselines are constructed, the problems encountered, and the results. We anticipate that the baselines can facilitate exciting future research to build human-robot dialogue systems for real-life tasks.

cs.CL↗