Xingyi Yang

Xingyi Yang
National University of Singapore | NUS · Department of Electrical & Computer Engineering

Doctor of Philosophy

About

64
Publications
31,718
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
923
Citations
Introduction
I am currently working on statistical machine learning for vision
Additional affiliations
September 2021 - present
National University of Singapore
Position
  • PhD Student
Education
September 2019 - June 2021
University of California, San Diego
Field of study
  • Signal and Image processing, Machine learning
July 2018 - September 2018
University of Ottawa
Field of study
  • Electrical and computer engineering
September 2015 - June 2019
Southeast University (China)
Field of study
  • Computer Engineering

Publications

Publications (64)
Conference Paper
Full-text available
Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad convergence. In this paper, we propose Kalman Optimi-zor (KO), an efficient stochastic optimization algorithm that...
Preprint
Full-text available
In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization~(KF). The core idea of KF lies in the modularization and assemblability of knowledge: given a pretrained network model as input, KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-...
Preprint
Full-text available
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous models pre-trained from distinct sources and with diverse architectures, the goal of DeRy, as its name implies, is to first dissect each model into distinctive building blocks, and t...
Preprint
Full-text available
This paper introduces a new learning paradigm termed Neural Metamorphosis (NeuMeta), which aims to build self-morphable neural networks. Contrary to crafting separate models for different architectures or sizes, NeuMeta directly learns the continuous weight manifold of neural networks. Once trained, we can sample weights for any-sized network direc...
Preprint
Full-text available
We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes swift and consistent 3D generation within a mere 5 minutes. At the heart of Vista3D lies a two-phase approach: the coarse phase and the fine phase. In the coarse phase,...
Preprint
Full-text available
Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the...
Preprint
Full-text available
This study addresses the challenge of accurately segmenting 3D Gaussian Splatting from 2D masks. Conventional methods often rely on iterative gradient descent to assign each Gaussian a unique label, leading to lengthy optimization and sub-optimal solutions. Instead, we propose a straightforward yet globally optimal solver for 3D-GS segmentation. Th...
Preprint
Generating dense multiview images from text prompts is crucial for creating high-fidelity 3D assets. Nevertheless, existing methods struggle with space-view correspondences, resulting in sparse and low-quality outputs. In this paper, we introduce CoSER, a novel consistent dense Multiview Text-to-Image Generator for Text-to-3D, achieving both effici...
Preprint
Full-text available
Diffusion models have recently achieved remarkable results for video generation. Despite the encouraging performances, the generated videos are typically constrained to a small number of frames, resulting in clips lasting merely a few seconds. The primary challenges in producing longer videos include the substantial memory requirements and the exte...
Preprint
Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic videos. Despite the promising results, a significant challenge remains: these models struggle to fully grasp complex compositional interactions between multiple concepts and...
Preprint
Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging task. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data and thus incre...
Preprint
Full-text available
Reconstructing 4D scenes from video inputs is a crucial yet challenging task. Conventional methods usually rely on the assumptions of multi-view video inputs, known camera parameters, or static scenes, all of which are typically absent under in-the-wild scenarios. In this paper, we relax all these constraints and tackle a highly ambitious but pract...
Preprint
Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature maps. To alleviate the computation cost, previous works rely on either fine-grained self-attentions restricte...
Preprint
Full-text available
Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive results on various generative tasks.Despite its promises, the learned representations of pre-trained DPMs, however, have not been fully understood. In this paper, we conduct an in-depth investigation of the representation power of DPMs, and propose a novel knowledge transfe...
Preprint
Full-text available
This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneous model reassembly to achieve personalized federated learning. In particul...
Conference Paper
Full-text available
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself...
Preprint
Full-text available
Machine learning society has witnessed the emergence of a myriad of Out-of-Distribution (OoD) algorithms, which address the distribution shift between the training and the testing distribution by searching for a unified predictor or invariant feature representation. However, the task of directly mitigating the distribution shift in the unseen testi...
Preprint
Full-text available
3D reconstruction from a single-RGB image in unconstrained real-world scenarios presents numerous challenges due to the inherent diversity and complexity of objects and environments. In this paper, we introduce Anything-3D, a methodical framework that ingeniously combines a series of visual-language models and the Segment-Anything object segmentati...
Preprint
Full-text available
Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms. Prior methods towards efficient DPM, however, have largely focused on accelerating the testing yet overlooked...
Chapter
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate due to privacy or copyright reasons. In practical scenarios, for instance, the model owner may wish to enable or disable the knowledge of specific tasks or specific samples...
Preprint
Full-text available
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline. Unlike conventional DD approaches that aim to produce distilled and representative samples, \emph{HaBa} explores decomposi...
Chapter
In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization (KF). The core idea of KF lies in the modularization and assemblability of knowledge: given a pretrained network model as input, KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-...
Preprint
Full-text available
In this study, we dive deep into the unique challenges in semi-supervised object detection~(SSOD). We observe that current detectors generally suffer from 3 inconsistency problems. 1) Assignment inconsistency, that the conventional assignment policy is sensitive to labeling noise. 2) Subtasks inconsistency, where the classification and regression p...
Article
Dry epidermal electrodes that can always form conformal contact with skin can be used for continuous long-term biopotential monitoring, which can provide vital information for disease diagnosis and rehabilitation. But, this application has been limited by the poor contact of dry electrodes on wet skin. Herein, we report a biocompatible fully organi...
Preprint
Full-text available
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate due to privacy or copyright reasons. In practical scenarios, for instance, the model owner may wish to enable or disable the knowledge of specific tasks or specific samples...
Preprint
Full-text available
Learning the dynamics of spatiotemporal events is a fundamental problem. Neural point processes enhance the expressivity of point process models with deep neural networks. However, most existing methods only consider temporal dynamics without spatial modeling. We propose Deep Spatiotemporal Point Process (DeepSTPP), a deep dynamics model that integ...
Conference Paper
Full-text available
In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched architectures are prone to adversarial attacks. A small perturbation of the input data can render the architecture...
Article
Full-text available
In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched architectures are prone to adversarial attacks. A small perturbation of the input data can render the architecture...
Poster
Full-text available
DSRNA: Differentiable Search of Robust Neural Architectures
Preprint
Full-text available
Medical report generation is one of the most challenging tasks in medical image analysis. Although existing approaches have achieved promising results, they either require a predefined template database in order to retrieve sentences or ignore the hierarchical nature of medical report generation. To address these issues, we propose MedWriter that i...
Preprint
Full-text available
In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched architectures are prone to adversarial attacks. A small perturbation of the input data can render the architecture...
Preprint
Full-text available
Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad convergence. In this paper, we propose \textbf{Filter Gradient Decent}~(FGD), an efficient stochastic optimization...
Chapter
Pedestrian detection is considered one of the most challenging problems in computer vision, as it involves the combination of classification and localization within a scene. Recently, convolutional neural networks (CNNs) have been demonstrated to achieve superior detection results compared to traditional approaches. Although YOLOv3 (an improved You...
Chapter
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a monocu...
Preprint
Full-text available
div>Pedestrian detection is considered one of the most challenging problems in computer vision, as it involves the combination of classification and localization within a scene. Recently, convolutional neural networks (CNNs) have been demonstrated to achieve superior detection results compared to traditional approaches. Although YOLOv3 (an improved...
Preprint
Full-text available
div>Pedestrian detection is considered one of the most challenging problems in computer vision, as it involves the combination of classification and localization within a scene. Recently, convolutional neural networks (CNNs) have been demonstrated to achieve superior detection results compared to traditional approaches. Although YOLOv3 (an improved...
Preprint
Full-text available
div>Pedestrian detection is considered one of the most challenging problems in computer vision, as it involves the combination of classification and localization within a scene. Recently, convolutional neural networks (CNNs) have been demonstrated to achieve superior detection results compared to traditional approaches. Although YOLOv3 (an improved...
Conference Paper
Full-text available
Pedestrian detection is considered one of the most challenging problems in computer vision, as it involves the combination of classification and localization within a scene. Recently, convolutional neural networks (CNNs) have been demonstrated to achieve superior detection results compared to traditional approaches. Although YOLOv3 (an improved You...
Conference Paper
Full-text available
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the \emph{absolute} scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a...
Preprint
Full-text available
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a monocu...
Preprint
Full-text available
Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously, the most dominant pretraining method is transfer learning (TL), which uses labeled data to learn a good representation network. Recently, a new pretraining approach -- self-supervised...
Preprint
Full-text available
Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously, the most dominant pretraining method is transfer learning (TL), which uses labeled data to learn a good representation network. Recently, a new pretraining approach -- self-supervised...
Preprint
Full-text available
Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously , the most dominant pretraining method is transfer learning (TL), which uses labeled data to learn a good representation network. Recently, a new pretraining approach-self-supervised le...
Preprint
Full-text available
To effectively train medical students to become qualified radiologists, a large number of X-ray images collected from patients with diverse medical conditions are needed. However, due to data privacy concerns, such images are typically difficult to obtain. To address this problem, we develop methods to generate view-consistent, high-fidelity, and h...
Preprint
Full-text available
Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this probl...
Preprint
Full-text available
div>Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this...
Preprint
Full-text available
div>Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this...
Preprint
Full-text available
Coronavirus disease 2019 (COVID-19) has infected more than 1.3 million individuals all over the world and caused more than 106,000 deaths. One major hurdle in controlling the spreading of this disease is the inefficiency and shortage of medical tests. There have been increasing efforts on developing deep learning methods to diagnose COVID-19 based...

Network

Cited By