arXiv subjects

Yujie Wang

Publications and source records attributed to Yujie Wang.

At least 109 records · Page 6Linked to original sources

arXiv2023

From creep to flow: Granular materials under cyclic shear

Granular materials such as sand, powders, and grains are omnipresent in daily life, industrial applications, and earth-science [1]. When unperturbed, they form stable structures that resemble the ones of other amorphous solids like metallic and colloidal glasses [2]. It is commonly conjectured that all these amorphous materials show a universal mechanical response when sheared slowly, i.e., to have an elastic regime, followed by yielding [3]. Here we use X-ray tomography to determine the microscopic dynamics of a cyclically sheared granular system in three dimensions. Independent of the shear amplitude $Γ$, the sample shows a cross-over from creep to diffusive dynamics, indicating that granular materials have no elastic response and always yield, in stark contrast to other glasses. The overlap function [4] reveals that at large $Γ$ yielding is a simple cross-over phenomenon, while for small $Γ$ it shows features of a first order transition with a critical point at $Γ\approx 0.1$ at which one finds a pronounced slowing down and dynamical heterogeneity. Our findings are directly related to the surface roughness of granular particles which induces a micro-corrugation to the potential energy landscape, thus creating relaxation channels that are absent in simple glasses. These processes must be understood for reaching an understanding of the complex relaxation dynamics of granular systems.

cond-mat.soft↗

arXiv2022

Experimental evidence of detailed balance in granular systems

The principle of detailed balance (DB) states that every kinetic transition in a system with many micro-states, $μ$, is balanced, on average, with the opposite transition, $μ_i\leftrightharpoonsμ_j$. Since its introduction by Boltzmann, this principle has been used by luminaries, such as Einstein, Eddington, Kramers, Pauli, Ehrenfest, Dirac, Onsager, and many others to derive significant results that underpin much of our scientific understanding. The current belief is that DB is satisfied only in equilibrium systems, while non-equilibrium steady states can only be balanced by cycles, such as $A\to B\to C\to A$. We show here experimentally that DB can exist and is commonly and robustly satisfied in a family of quasi-statically cyclically sheared granular systems. We further study the approach to DB as a function of system size and time. Given the significant impact that this principle has had on equilibrium systems, we believe that this discovery paves the way for better models of the dynamics of non-equilibrium systems.

cond-mat.soft↗

arXiv2022

Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism

Transformer models have achieved state-of-the-art performance on various domains of applications and gradually becomes the foundations of the advanced large deep learning (DL) models. However, how to train these models over multiple GPUs efficiently is still challenging due to a large number of parallelism choices. Existing DL systems either rely on manual efforts to make distributed training plans or apply parallelism combinations within a very limited search space. In this approach, we propose Galvatron, a new system framework that incorporates multiple popular parallelism dimensions and automatically finds the most efficient hybrid parallelism strategy. To better explore such a rarely huge search space, we 1) involve a decision tree to make decomposition and pruning based on some reasonable intuitions, and then 2) design a dynamic programming search algorithm to generate the optimal plan. Evaluations on four representative Transformer workloads show that Galvatron could perform automatically distributed training with different GPU memory budgets. Among all evluated scenarios, Galvatron always achieves superior system throughput compared to previous work with limited parallelism.

cs.LG↗

arXiv2022

SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scene

We present a 3D generative model for general natural scenes. Lacking necessary volumes of 3D data characterizing the target scene, we propose to learn from a single scene. Our key insight is that a natural scene often contains multiple constituents whose geometry, texture, and spatial arrangements follow some clear patterns, but still exhibit rich variations over different regions within the same scene. This suggests localizing the learning of a generative model on substantial local regions. Hence, we exploit a multi-scale convolutional network, which possesses the spatial locality bias in nature, to learn from the statistics of local regions at multiple scales within a single scene. In contrast to existing methods, our learning setup bypasses the need to collect data from many homogeneous 3D scenes for learning common features. We coin our method SinGRAV, for learning a Generative RAdiance Volume from a Single natural scene. We demonstrate the ability of SinGRAV in generating plausible and diverse variations from a single scene, the merits of SinGRAV over state-of-the-art generative neural scene methods, as well as the versatility of SinGRAV by its use in a variety of applications, spanning 3D scene editing, composition, and animation. Code and data will be released to facilitate further research.

cs.CV↗

arXiv2022

Equivalence of fluctuation-dissipation and Edwards' temperature in cyclically sheared granular systems

Using particle trajectory data obtained from x-ray tomography, we determine two kinds of effective temperatures in a cyclically sheared granular system. The first one is obtained from the fluctuation-dissipation theorem which relates the diffusion and mobility of lighter tracer particles immersed in the system. The second is the Edwards compactivity defined via the packing volume fluctuations. We find robust excellent agreement between these two temperatures, independent of the type of the tracers, cyclic shear amplitudes, and particle surface roughness. We further elucidate that in granular systems the viscous-like drag force is due to the broken symmetry of the local contact geometry.

cond-mat.soft↗

arXiv2022

PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection

In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance. To address the problems incurred by noisy pseudo boxes, we design Noisy Pseudo box Learning (NPL) that includes Prediction-guided Label Assignment (PLA) and Positive-proposal Consistency Voting (PCV). PLA relies on model predictions to assign labels and makes it robust to even coarse pseudo boxes; while PCV leverages the regression consistency of positive proposals to reflect the localization quality of pseudo boxes. Furthermore, in consistency training, we propose Multi-view Scale-invariant Learning (MSL) that includes mechanisms of both label- and feature-level consistency, where feature consistency is achieved by aligning shifted feature pyramids between two images with identical content but varied scales. On COCO benchmark, our method, termed PSEudo labeling and COnsistency training (PseCo), outperforms the SOTA (Soft Teacher) by 2.0, 1.8, 2.0 points under 1%, 5%, and 10% labelling ratios, respectively. It also significantly improves the learning efficiency for SSOD, e.g., PseCo halves the training time of the SOTA approach but achieves even better performance. Code is available at https://github.com/ligang-cs/PseCo.

cs.CV↗

arXiv2022

DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection

The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted label assignment. However, the sparse-to-dense paradigm complicates the pipeline of SSOD, and simultaneously neglects the powerful direct, dense teacher supervision. In this paper, we attempt to directly leverage the dense guidance of teacher to supervise student training, i.e., the dense-to-dense paradigm. Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels. INC leads the student to group candidate boxes into clusters in NMS as the teacher does, which is implemented by learning grouping information revealed in NMS procedure of the teacher. After obtaining the same grouping scheme as the teacher via INC, the student further imitates the rank distribution of the teacher over clustered candidates through Rank Matching. With the proposed INC and RM, we integrate Dense Teacher Guidance into Semi-Supervised Object Detection (termed DTG-SSOD), successfully abandoning sparse pseudo labels and enabling more informative learning on unlabeled data. On COCO benchmark, our DTG-SSOD achieves state-of-the-art performance under various labelling ratios. For example, under 10% labelling ratio, DTG-SSOD improves the supervised baseline from 26.9 to 35.9 mAP, outperforming the previous best method Soft Teacher by 1.9 points.

cs.CV↗

arXiv2022

BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling

This paper describes the BLCU-ICALL system used in the SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings, the Definition Modeling subtrack, achieving 1st on Italian, 2nd on Spanish and Russian, and 3rd on English and French. We propose a transformer-based multitasking framework to explore the task. The framework integrates multiple embedding architectures through the cross-attention mechanism, and captures the structure of glosses through a masking language model objective. Additionally, we also investigate a simple but effective model ensembling strategy to further improve the robustness. The evaluation results show the effectiveness of our solution. We release our code at: https://github.com/blcuicall/SemEval2022-Task1-DM.

cs.CL↗

arXiv2022

The Tree Loss: Improving Generalization with Many Classes

Multi-class classification problems often have many semantically similar classes. For example, 90 of ImageNet's 1000 classes are for different breeds of dog. We should expect that these semantically similar classes will have similar parameter vectors, but the standard cross entropy loss does not enforce this constraint. We introduce the tree loss as a drop-in replacement for the cross entropy loss. The tree loss re-parameterizes the parameter matrix in order to guarantee that semantically similar classes will have similar parameter vectors. Using simple properties of stochastic gradient descent, we show that the tree loss's generalization error is asymptotically better than the cross entropy loss's. We then validate these theoretical results on synthetic data, image data (CIFAR100, ImageNet), and text data (Twitter).

cs.LG↗

arXiv2022

Channel Estimation for Wideband MmWave MIMO OFDM System Exploiting Block Sparsity

In this letter, we investigate time-domain channel estimation for wideband millimeter wave (mmWave) MIMO OFDM system. By transmitting frequency-domain pilot symbols as well as different beamforming vectors, we observe that the time-domain mmWave MIMO channels exhibit channel delay sparsity and especially block sparsity among different spatial directions. Then we propose a time-domain channel estimation exploiting block sparsity (TDCEBS) scheme, which always aims at finding the best nonzero block achieving the largest projection of the residue at each iterations. In particular, we evaluate the system performance using the QuaDRiGa which is recommended by 5G New Radio to generate wideband mmWave MIMO channels. The effectiveness of the proposed TDCEBS scheme is verified by the simulation results, as the proposed scheme outperforms the existing schemes.

cs.IT↗

arXiv2022

INTERN: A New Learning Paradigm Towards General Vision

Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However, down the road, a key challenge awaits us, that is, our capability of meeting rapidly-growing scenario-specific demands is severely limited by the cost of acquiring a commensurate amount of training data. This difficult situation is in essence due to limitations of the mainstream learning paradigm: we need to train a new model for each new scenario, based on a large quantity of well-annotated data and commonly from scratch. In tackling this fundamental problem, we move beyond and develop a new learning paradigm named INTERN. By learning with supervisory signals from multiple sources in multiple stages, the model being trained will develop strong generalizability. We evaluate our model on 26 well-known datasets that cover four categories of tasks in computer vision. In most cases, our models, adapted with only 10% of the training data in the target domain, outperform the counterparts trained with the full set of data, often by a significant margin. This is an important step towards a promising prospect where such a model with general vision capability can dramatically reduce our reliance on data, thus expediting the adoption of AI technologies. Furthermore, revolving around our new paradigm, we also introduce a new data system, a new architecture, and a new benchmark, which, together, form a general vision ecosystem to support its future development in an open and inclusive manner. See project website at https://opengvlab.shlab.org.cn .

cs.CV↗

arXiv2022

Neural Implicit 3D Shapes from Single Images with Spatial Patterns

Neural implicit functions have achieved impressive results for reconstructing 3D shapes from single images. However, the image features for describing 3D point samplings of implicit functions are less effective when significant variations of occlusions, views, and appearances exist from the image. To better encode image features, we study a geometry-aware convolutional kernel to leverage geometric relationships of point samplings by the proposed \emph{spatial pattern}, i.e., a structured point set. Specifically, the kernel operates at 2D projections of 3D points from the spatial pattern. Supported by the spatial pattern, the 2D kernel encodes geometric information that is crucial for 3D reconstruction tasks, while traditional ones mainly consider appearance information. Furthermore, to enable the network to discover more adaptive spatial patterns for further capturing non-local contextual information, the kernel is devised to be deformable manipulated by a spatial pattern generator. Experimental results on both synthetic and real datasets demonstrate the superiority of the proposed method. Pre-trained models, codes, and data are available at https://github.com/yixin26/SVR-SP.

cs.CV↗

arXiv2021

V2V-Based Task Offloading and Resource Allocation in Vehicular Edge Computing Networks

In the research and application of vehicle ad hoc networks (VANETs), it is often assumed that vehicles obtain cloud computing services by accessing to roadside units (RSUs). However, due to the problems of insufficient construction quantity, limited communication range and overload of calculation load of roadside units, the calculation mode relying only on vehicle to roadside units is difficult to deal with complex and changeable calculation tasks. In this paper, when the roadside unit is missing, the vehicle mobile unit is regarded as a natural edge computing node to make full use of the excess computing power of mobile vehicles and perform the offloading task of surrounding mobile vehicles in time. In this paper, the OPFTO framework is designed, an improved task allocation algorithm HGSA is proposed, and the pre-filtering process is designed with full consideration of the moving characteristics of vehicles. In addition, vehicle simulation experiments show that the proposed strategy has the advantages of low delay and high accuracy compared with other task scheduling strategies, which provides a reference scheme for the construction of Urban Intelligent Transportation in the future.

cs.DC↗

arXiv2021

Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation

Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD methods for object detection is non-trivial. In this work, we elaborately study the behaviour difference between the teacher and student detection models, and obtain two intriguing observations: First, the teacher and student rank their detected candidate boxes quite differently, which results in their precision discrepancy. Second, there is a considerable gap between the feature response differences and prediction differences between teacher and student, indicating that equally imitating all the feature maps of the teacher is the sub-optimal choice for improving the student's accuracy. Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively. RM takes the rank of candidate boxes from teachers as a new form of knowledge to distill, which consistently outperforms the traditional soft label distillation. PFI attempts to correlate feature differences with prediction differences, making feature imitation directly help to improve the student's accuracy. On MS COCO and PASCAL VOC benchmarks, extensive experiments are conducted on various detectors with different backbones to validate the effectiveness of our method. Specifically, RetinaNet with ResNet50 achieves 40.4% mAP in MS COCO, which is 3.5% higher than its baseline, and also outperforms previous KD methods.

cs.CV↗

arXiv2021

Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation

The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive scanning order during the sampling phase. This leads the existing VQ series models to hardly escape the trap of lacking global information. Denoising Diffusion Probabilistic Models (DDPM) in the continuous domain have shown a capability to capture the global context, while generating high-quality images. In the discrete state space, some works have demonstrated the potential to perform text generation and low resolution image generation. We show that with the help of a content-rich discrete visual codebook from VQ-VAE, the discrete diffusion model can also generate high fidelity images with global context, which compensates for the deficiency of the classical autoregressive model along pixel space. Meanwhile, the integration of the discrete VAE with the diffusion model resolves the drawback of conventional autoregressive models being oversized, and the diffusion model which demands excessive time in the sampling process when generating images. It is found that the quality of the generated images is heavily dependent on the discrete visual codebook. Extensive experiments demonstrate that the proposed Vector Quantised Discrete Diffusion Model (VQ-DDM) is able to achieve comparable performance to top-tier methods with low complexity. It also demonstrates outstanding advantages over other vectors quantised with autoregressive models in terms of image inpainting tasks without additional training.

cs.CV↗

arXiv2021

One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data

The foundation model is not the last chapter of the model production pipeline. Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application. In this paper, we proposed a universal transfer framework: One to Transfer All (OTA) to transfer any Vision Foundation Model (VFM) to any downstream tasks with few downstream data. We first transfer a VFM to a task-specific model by Image Re-representation Fine-tuning (IRF) then distilling knowledge from a task-specific model to a deployed model with data produced by Downstream Image-Guided Generation (DIGG). OTA has no dependency on upstream data, VFM, and downstream tasks when transferring. It also provides a way for VFM researchers to release their upstream information for better transferring but not leaking data due to privacy requirements. Massive experiments validate the effectiveness and superiority of our methods in few data setting. Our code will be released.

cs.CV↗

arXiv2021

Hierarchical Segment-based Optimization for SLAM

This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system. First we propose a reliable trajectory segmentation method that can be used to increase efficiency in the back-end optimization. Then we propose a buffer mechanism for the first time to improve the robustness of the segmentation. During the optimization, we use global information to optimize the frames with large error, and interpolation instead of optimization to update well-estimated frames to hierarchically allocate the amount of computation according to error of each frame. Comparative experiments on the benchmark show that our method greatly improves the efficiency of optimization with almost no drop in accuracy, and outperforms existing high-efficiency optimization method by a large margin.

cs.RO↗

arXiv2021

Critical behaviors of jamming in cyclically sheared frictional hard granular particles

In stark contrast to the jamming of frictionless hard-sphere (hard-disk if in two dimensions) packings, the critical jamming of frictional packings is much more elusive and still under intense debate. Here we show that frictional hard-disk packings self-organize near a critical jamming state when subjected to quasi-static steady-state cyclic shear, displaying scale-free fluctuations in particle velocity fields as characterized by the power spectra $E(k)\propto k^{-α}$ for both longitudinal and transverse modes in wavevector space, with $α\approx2.0\pm0.15$, and the nearly flat spectra $E(ω)\propto const.$ in angular frequency domain. Our findings agree quantitatively with the predictions of the Langevin-type effective medium theory of S. Henkes and coworkers with two diverging length scales associated respectively with the longitudinal and transverse modes, showing a hallmark of critical behaviors of jamming. Moreover, our findings are consistent with the conceptual framework of general isostaticity but with a key difference that the system self-organizes to a critical jamming state through a strong coupling of mechanical structure and dynamics. Our findings are important in providing microscopic mechanism in understanding the nonlocal rheologies and guide principles in developing constitutive relations of real granular materials.

cond-mat.soft↗