arXiv subjects

Yanbo Wang

Publications and source records attributed to Yanbo Wang.

104 records · Page 6Linked to original sources

arXiv2024

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous methods, starting from reconstructing a single data point and then relaxing the single-image limit to batch level, are only tested under hard label constraints. Even for single-image reconstruction, we still lack an analysis-based algorithm to recover augmented soft labels. In this work, we change the focus from enlarging batchsize to investigating the hard label constraints, considering a more realistic circumstance where label smoothing and mixup techniques are used in the training process. In particular, we are the first to initiate a novel algorithm to simultaneously recover the ground-truth augmented label and the input feature of the last fully-connected layer from single-input gradients, and provide a necessary condition for any analytical-based label recovery methods. Extensive experiments testify to the label recovery accuracy, as well as the benefits to the following image reconstruction. We believe soft labels in classification tasks are worth further attention in gradient inversion attacks.

cs.CR↗

arXiv2024

NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising

In recent years, there have been significant advancements in 3D reconstruction and dense RGB-D SLAM systems. One notable development is the application of Neural Radiance Fields (NeRF) in these systems, which utilizes implicit neural representation to encode 3D scenes. This extension of NeRF to SLAM has shown promising results. However, the depth images obtained from consumer-grade RGB-D sensors are often sparse and noisy, which poses significant challenges for 3D reconstruction and affects the accuracy of the representation of the scene geometry. Moreover, the original hierarchical feature grid with occupancy value is inaccurate for scene geometry representation. Furthermore, the existing methods select random pixels for camera tracking, which leads to inaccurate localization and is not robust in real-world indoor environments. To this end, we present NeSLAM, an advanced framework that achieves accurate and dense depth estimation, robust camera tracking, and realistic synthesis of novel views. First, a depth completion and denoising network is designed to provide dense geometry prior and guide the neural implicit representation optimization. Second, the occupancy scene representation is replaced with Signed Distance Field (SDF) hierarchical scene representation for high-quality reconstruction and view synthesis. Furthermore, we also propose a NeRF-based self-supervised feature tracking algorithm for robust real-time tracking. Experiments on various indoor datasets demonstrate the effectiveness and accuracy of the system in reconstruction, tracking quality, and novel view synthesis.

cs.CV↗

arXiv2024

Extreme Precipitation Nowcasting using Transformer-based Generative Models

This paper presents an innovative approach to extreme precipitation nowcasting by employing Transformer-based generative models, namely NowcastingGPT with Extreme Value Loss (EVL) regularization. Leveraging a comprehensive dataset from the Royal Netherlands Meteorological Institute (KNMI), our study focuses on predicting short-term precipitation with high accuracy. We introduce a novel method for computing EVL without assuming fixed extreme representations, addressing the limitations of current models in capturing extreme weather events. We present both qualitative and quantitative analyses, demonstrating the superior performance of the proposed NowcastingGPT-EVL in generating accurate precipitation forecasts, especially when dealing with extreme precipitation events. The code is available at \url{https://github.com/Cmeo97/NowcastingGPT}.

cs.LG↗

arXiv2024

Slot-VAE: Object-Centric Scene Generation with Slot Attention

Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the Slot-VAE, a generative model that integrates slot attention with the hierarchical VAE framework for object-centric structured scene generation. For each image, the model simultaneously infers a global scene representation to capture high-level scene structure and object-centric slot representations to embed individual object components. During generation, slot representations are generated from the global scene representation to ensure coherent scene structures. Our extensive evaluation of the scene generation ability indicates that Slot-VAE outperforms slot representation-based generative baselines in terms of sample quality and scene structure accuracy.

cs.CV↗

arXiv2023

TwiBot-22: Towards Graph-Based Twitter Bot Detection

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at https://twibot22.github.io/

cs.SI↗

arXiv2023

High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets

The last decades are marked by massive and diverse image data, which shows increasingly high resolution and quality. However, some images we obtained may be corrupted, affecting the perception and the application of downstream tasks. A generic method for generating a high-quality image from the degraded one is in demand. In this paper, we present a novel GAN inversion framework that utilizes the powerful generative ability of StyleGAN-XL for this problem. To ease the inversion challenge with StyleGAN-XL, Clustering \& Regularize Inversion (CRI) is proposed. Specifically, the latent space is firstly divided into finer-grained sub-spaces by clustering. Instead of initializing the inversion with the average latent vector, we approximate a centroid latent vector from the clusters, which generates an image close to the input image. Then, an offset with a regularization term is introduced to keep the inverted latent vector within a certain range. We validate our CRI scheme on multiple restoration tasks (i.e., inpainting, colorization, and super-resolution) of complex natural images, and show preferable quantitative and qualitative results. We further demonstrate our technique is robust in terms of data and different GAN models. To our best knowledge, we are the first to adopt StyleGAN-XL for generating high-quality natural images from diverse degraded inputs. Code is available at https://github.com/Booooooooooo/CRI.

cs.CV↗

arXiv2022

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

cs.CV↗

arXiv2021

Towards Compact Single Image Super-Resolution via Contrastive Self-distillation

Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices. In this paper, we proposed a novel contrastive self-distillation (CSD) framework to simultaneously compress and accelerate various off-the-shelf SR models. In particular, a channel-splitting super-resolution network can first be constructed from a target teacher network as a compact student network. Then, we propose a novel contrastive loss to improve the quality of SR images and PSNR/SSIM via explicit knowledge transfer. Extensive experiments demonstrate that the proposed CSD scheme effectively compresses and accelerates several standard SR models such as EDSR, RCAN and CARN. Code is available at https://github.com/Booooooooooo/CSD.

cs.CV↗

arXiv2021

Third-Order Statistics Reconstruction from Compressive Measurements

Estimation of third-order statistics relies on the availability of a huge amount of data records, which can pose severe challenges on the data collecting hardware in terms of considerable storage costs, overwhelming energy consumption, and unaffordably high sampling rate especially when dealing with high-dimensional data such as wideband signals. To overcome these challenges, this paper focuses on the reconstruction of the third-order cumulants under the compressive sensing framework. Specifically, this paper derives a transformed linear system that directly connects the cross-cumulants of compressive measurements to the desired third-order statistics. We provide sufficient conditions for lossless third-order statistics reconstruction via solving simple least-squares, along with the strongest achievable compression ratio. To reduce the computational burden, we also propose an approach to recover diagonal cumulant slices directly from compressive measurements, which is useful when the cumulant slices are sufficient for the inference task at hand. All the proposed techniques are tested via extensive simulations. The developed joint sampling and reconstruction approach to third-order statistics estimation is able to reduce the required sampling rates significantly by exploiting the cumulant structure resulting from signal stationarity, even in the absence of any sparsity constraints on the signal or cumulants.

eess.SP↗

arXiv2020

Hand-Gesture-Recognition Based Text Input Method for AR/VR Wearable Devices

Static and dynamic hand movements are basic way for human-machine interactions. To recognize and classify these movements, first these movements are captured by the cameras mounted on the augmented reality (AR) or virtual reality (VR) wearable devices. The hand is segmented using segmentation method and its gestures are passed to hand gesture recognition algorithm, which depends on depth-wise separable convolutional neural network for training, testing and finally running smoothly on mobile AR/VR devices, while maintaining the accuracy and balancing the load. A number of gestures are processed for identification of right gesture and to classify the gesture and ignore the all intermittent gestures. With proposed method, a user can write letters and numbers in air by just moving his/her hand in air. Gesture based operations are performed, and trajectory of hand is recorded as handwritten text. Finally, that handwritten text is processed for the text recognition.

cs.HC↗

arXiv2020

Unique continuation property with partial information for two-dimensional anisotropic elasticity systems

In this paper, we establish a novel unique continuation property for two-dimensional anisotropic elasticity systems with partial information. More precisely, given a homogeneous elasticity system in a domain, we investigate the unique continuation by assuming only the vanishing of one component of the solution in a subdomain. Using the corresponding Riemann function, we prove that the solution vanishes in the whole domain provided that the other component vanishes at one point up to its second derivatives. Further, we construct several examples showing the possibility of further reducing the additional information of the other component. This result possesses remarkable significance in both theoretical and practical aspects because the required data is almost halved for the unique determination of the whole solution.

math.AP↗

arXiv2018

Multi-Scale DenseNet-Based Electricity Theft Detection

Electricity theft detection issue has drawn lots of attention during last decades. Timely identification of the electricity theft in the power system is crucial for the safety and availability of the system. Although sustainable efforts have been made, the detection task remains challenging and falls short of accuracy and efficiency, especially with the increase of the data size. Recently, convolutional neural network-based methods have achieved better performance in comparison with traditional methods, which employ handcrafted features and shallow-architecture classifiers. In this paper, we present a novel approach for automatic detection by using a multi-scale dense connected convolution neural network (multi-scale DenseNet) in order to capture the long-term and short-term periodic features within the sequential data. We compare the proposed approaches with the classical algorithms, and the experimental results demonstrate that the multiscale DenseNet approach can significantly improve the accuracy of the detection. Moreover, our method is scalable, enabling larger data processing while no handcrafted feature engineering is needed.

cs.CV↗

arXiv2013

Co-development of significant elastic and reversible plastic deformation in nanowires

When a material is subjected to an applied stress, the material will experience recoverable elastic deformation followed by permanent plastic deformation at the point when the applied stress exceeds the yield stress of the material. Microscopically, the onset of the plasticity usually indicates the activation of dislocation motion, which is considered to be the primary mechanism of plastic deformation. Once plastic deformation is initiated, further elastic deformation is negligible owing to the limited increase in the flow stress caused by work hardening. Here we present experimental evidence and quantitative analysis of simultaneous development of significant elastic deformation and dislocation-based plastic deformation in single crystal GaAs nanowires (NWs) under bending deformation up to a total strain of ~ 6%. The observation is in sharp contrast to the previous notions regarding the deformation modes. Most of the plastic deformation recovers spontaneously when the external stress is released, and therefore resembles an elastic deformation process.

cond-mat.mtrl-sci↗

arXiv2011

Kinetics of Muller's Ratchet from Adaptive Landscape Viewpoint

Background: The accumulation of deleterious mutations of a population directly contributes to the fate as to how long the population would exist. Muller's ratchet provides a quantitative framework to study the effect of accumulation. Adaptive landscape as a powerful concept in system biology provides a handle to describe complex and rare biological events. In this article we study the evolutionary process of a population exposed to Muller's ratchet from the new viewpoint of adaptive landscape which allows us estimate the single click of the ratchet starting with an intuitive understanding. Methods: We describe how Wright-Fisher process maps to Muller's ratchet. We analytically construct adaptive landscape from general diffusion equation. It shows that the construction is dynamical and the adaptive landscape is independent of the existence and normalization of the stationary distribution. We generalize the application of diffusion model from adaptive landscape viewpoint. Results: We develop a novel method to describe the dynamical behavior of the population exposed to Muller's ratchet, and analytically derive the decaying time of the fittest class of populations as a mean first passage time. Most importantly, we describe the absorption phenomenon by adaptive landscape, where the stationary distribution is non-normalizable. These results suggest the method may be used to understand the mechanism of populations evolution and describe the biological processes quantitatively.

q-bio.PE↗