arXiv subjects

Haoyang Zhang

Publications and source records attributed to Haoyang Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2023

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes. However, prevailing methodologies primarily focus on voxel-wise feature aggregation, while neglecting instance semantics and scene context. In this paper, we present a novel paradigm termed Symphonies (Scene-from-Insts), that delves into the integration of instance queries to orchestrate 2D-to-3D reconstruction and 3D scene modeling. Leveraging our proposed Serial Instance-Propagated Attentions, Symphonies dynamically encodes instance-centric semantics, facilitating intricate interactions between image-based and volumetric domains. Simultaneously, Symphonies enables holistic scene comprehension by capturing context through the efficient fusion of instance queries, alleviating geometric ambiguity such as occlusion and perspective errors through contextual scene reasoning. Experimental results demonstrate that Symphonies achieves state-of-the-art performance on challenging benchmarks SemanticKITTI and SSCBench-KITTI-360, yielding remarkable mIoU scores of 15.04 and 18.58, respectively. These results showcase the paradigm's promising advancements. The code is available at https://github.com/hustvl/Symphonies.

cs.CV↗

arXiv2023

G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrations

To break the GPU memory wall for scaling deep learning workloads, a variety of architecture and system techniques have been proposed recently. Their typical approaches include memory extension with flash memory and direct storage access. However, these techniques still suffer from suboptimal performance and introduce complexity to the GPU memory management, making them hard to meet the scalability requirement of deep learning workloads today. In this paper, we present a unified GPU memory and storage architecture named G10 driven by the fact that the tensor behaviors of deep learning workloads are highly predictable. G10 integrates the host memory, GPU memory, and flash memory into a unified memory space, to scale the GPU memory capacity while enabling transparent data migrations. Based on this unified GPU memory and storage architecture, G10 utilizes compiler techniques to characterize the tensor behaviors in deep learning workloads. Therefore, it can schedule data migrations in advance by considering the available bandwidth of flash memory and host memory. The cooperative mechanism between deep learning compilers and the unified memory architecture enables G10 to hide data transfer overheads in a transparent manner. We implement G10 based on an open-source GPU simulator. Our experiments demonstrate that G10 outperforms state-of-the-art GPU memory solutions by up to 1.75$\times$, without code modifications to deep learning workloads. With the smart data migration mechanism, G10 can reach 90.3\% of the performance of the ideal case assuming unlimited GPU memory.

cs.AR↗

arXiv2023

The role of hydrodynamics for the spatial distribution of high-temperature hydrothermal vent-endemic fauna in the deep ocean environment

Active hydrothermal vents provide the surrounding submarine environment with substantial amounts of matter and energy, thus serving as important habitats for diverse megabenthic communities in the deep ocean and constituting a unique, highly productive chemosynthetic ecosystem on Earth. Vent-endemic biological communities gather near the venting site and are usually not found beyond a distance of the order of 100 m from the vent. This is surprising because one would actually expect matter ejected from high-temperature vents, which generate highly turbulent buoyancy plumes, to be suspended and carried far away by the plume flows and deep-sea currents. Here, we study this problem from a fluid dynamics perspective by simulating the vent hydrodynamics using a numerical model that couples the plume flow with induced matter and energy transport. We find that both low- and high-temperature vents deposit most vent matter relatively close to the plume. In particular, the tendency of turbulent buoyancy plumes to carry matter far away is strongly counteracted by generated entrainment flows back into the plume stem. The deposition ranges of organic and inorganic hydrothermal particles obtained from the simulations for various natural high-temperature vents are consistent with the observed maximum spatial extent of biological communities, evidencing that plume hydrodynamics exercises strong control over the spatial distribution of vent-endemic fauna. While other factors affecting the spatial distribution of vent-endemic fauna, such as geology and geochemistry, are site-specific, the main physical features of plume hydrodynamics unraveled in this study are largely site-unspecific and therefore universal across vent sites on Earth.

physics.flu-dyn↗

arXiv2023

The detection of possible $γ$-ray quasi-periodic modulation with $\sim$600 days from the blazar S2 0109+22

In this work, we analyzed the long term gamma-ray data by a Fermi Large Area Telescope (Fermi-LAT) of blazar S2 0109+22, ranging from 2008 to 2023. The quasi-periodic oscillations (QPOs) of blazars aided in investigating the physical properties of internal supermassive black holes, the nature of variability, and the underlying radiation mechanism. We employed four different methods--Weighted Wavelet Z-transform, Lomb-Scargle periodogram, REDFIT and phase folded light curve analysis, for searching QPO signals. Our analysis identified a possible QPO behavior with a periodicity of $\sim$600 days in November 2013 to January 2023 at a significance level of 3.5 $σ$. This QPO signal sustained $\sim$9 years, corresponding to 5.6 cycles, which was in good agreement with the previously observed of periodicity $\sim$657 days in radio. We explained this phenomenon based on the accretion model and the lighthouse effect, in a binary black hole system.

astro-ph.HE↗

arXiv2023

Search for X-ray Quasi-periodicity of six AGNs using Gaussian Process method

The quasi-periodic oscillations (QPOs) found in active galactic nuclei (AGNs) are a very interesting observational phenomenon implying an unknown physical mechanism around supermassive black holes. Several AGNs have been found to have QPO phenomena in the X-ray energy band. Long-duration X-ray observations were collected and reduced for six AGNs with a suspected QPO. The Gaussian process (GP) model celerite was used to fit the light curves and to search for the quasi-periodicity behavior. The power spectral density and parameter posterior distributions of each light curve were calculated with the optimal model. Of the six AGNs, only RE J1034+396 was found to have a QPO of about 3600 s. The other five sources do not show QPO modulation behavior. We propose that a hot spot on the accretion disk is a possible physical mechanism resulting in this quasi-periodic behavior of AGNs.

astro-ph.HE↗

arXiv2023

Super-resolution of Ray-tracing Channel Simulation via Attention Mechanism based Deep Learning Model

As an emerging approach, deep learning plays an increasingly influential role in channel modeling. Traditional ray tracing (RT) methods of channel modeling tend to be inefficient and expensive. In this paper, we present a super-resolution (SR) model for channel characteristics. Residual connection and attention mechanism are applied to this convolutional neural network (CNN) model. Experiments prove that the proposed model can reduce the noise interference generated in the SR process and solve the problem of low efficiency of RT. The mean absolute error of our channel SR model on the PL achieves the effect of 2.82 dB with scale factor 2, the same accuracy as RT took only 52\% of the time in theory. Compared with vision transformer (ViT), the proposed model also demonstrates less running time and computing cost in SR of channel characteristics.

eess.SP↗

arXiv2023

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

Video instance segmentation (VIS) aims at segmenting and tracking objects in videos. Prior methods typically generate frame-level or clip-level object instances first and then associate them by either additional tracking heads or complex instance matching algorithms. This explicit instance association approach increases system complexity and fails to fully exploit temporal cues in videos. In this paper, we design a simple, fast and yet effective query-based framework for online VIS. Relying on an instance query and proposal propagation mechanism with several specially developed components, this framework can perform accurate instance association implicitly. Specifically, we generate frame-level object instances based on a set of instance query-proposal pairs propagated from previous frames. This instance query-proposal pair is learned to bind with one specific object across frames through conscientiously developed strategies. When using such a pair to predict an object instance on the current frame, not only the generated instance is automatically associated with its precursors on previous frames, but the model gets a good prior for predicting the same object. In this way, we naturally achieve implicit instance association in parallel with segmentation and elegantly take advantage of temporal clues in videos. To show the effectiveness of our method InsPro, we evaluate it on two popular VIS benchmarks, i.e., YouTube-VIS 2019 and YouTube-VIS 2021. Without bells-and-whistles, our InsPro with ResNet-50 backbone achieves 43.2 AP and 37.6 AP on these two benchmarks respectively, outperforming all other online VIS methods.

cs.CV↗

arXiv2022

MovieCLIP: Visual Scene Recognition in Movies

Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes. Domain specific challenges associated with visual scenes in movies include transitions, person coverage, and a wide array of real-life and fictional scenarios. Existing visual scene datasets in movies have limited taxonomies and don't consider the visual scene transition within movie clips. In this work, we address the problem of visual scene recognition in movies by first automatically curating a new and extensive movie-centric taxonomy of 179 scene labels derived from movie scripts and auxiliary web-based video datasets. Instead of manual annotations which can be expensive, we use CLIP to weakly label 1.12 million shots from 32K movie clips based on our proposed taxonomy. We provide baseline visual models trained on the weakly labeled dataset called MovieCLIP and evaluate them on an independent dataset verified by human raters. We show that leveraging features from models pretrained on MovieCLIP benefits downstream tasks such as multi-label scene and genre classification of web videos and movie trailers.

cs.CV↗

arXiv2022

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation

This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth regression head to panoptic segmentation (PS) networks, resulting in two independent task branches. This neglects the mutually-beneficial relations between these two tasks, thus failing to exploit handy instance-level semantic cues to boost depth accuracy while also producing sub-optimal depth maps. To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks. Specifically, instead of predicting depth for all pixels at a time, we generate instance-specific kernels to predict depth and segmentation masks for each instance. Moreover, leveraging the instance-wise depth estimation scheme, we add additional instance-level depth cues to assist with supervising the depth learning via a new depth loss. Extensive experiments on Cityscapes-DPS and SemKITTI-DPS show the effectiveness and promise of our method. We hope our unified solution to DPS can lead a new paradigm in this area. Code is available at https://github.com/NaiyuGao/PanopticDepth.

cs.CV↗

arXiv2021

Evaluating the Impact of Semantic Segmentation and Pose Estimation on Dense Semantic SLAM

Recent Semantic SLAM methods combine classical geometry-based estimation with deep learning-based object detection or semantic segmentation. In this paper we evaluate the quality of semantic maps generated by state-of-the-art class- and instance-aware dense semantic SLAM algorithms whose codes are publicly available and explore the impacts both semantic segmentation and pose estimation have on the quality of semantic maps. We obtain these results by providing algorithms with ground-truth pose and/or semantic segmentation data available from simulated environments. We establish that semantic segmentation is the largest source of error through our experiments, dropping mAP and OMQ performance by up to 74.3% and 71.3% respectively.

cs.RO↗

arXiv2021

SWA Object Detection

Do you want to improve 1.0 AP for your object detector without any inference cost and any change to your detector? Let us tell you such a recipe. It is surprisingly simple: train your detector for an extra 12 epochs using cyclical learning rates and then average these 12 checkpoints as your final detection model}. This potent recipe is inspired by Stochastic Weights Averaging (SWA), which is proposed in arXiv:1803.05407 for improving generalization in deep neural networks. We found it also very effective in object detection. In this technique report, we systematically investigate the effects of applying SWA to object detection as well as instance segmentation. Through extensive experiments, we discover the aforementioned workable policy of performing SWA in object detection, and we consistently achieve $\sim$1.0 AP improvement over various popular detectors on the challenging COCO benchmark, including Mask RCNN, Faster RCNN, RetinaNet, FCOS, YOLOv3 and VFNet. We hope this work will make more researchers in object detection know this technique and help them train better object detectors. Code is available at: https://github.com/hyz-xmaster/swa_object_detection .

cs.CV↗

arXiv2021

VarifocalNet: An IoU-aware Dense Object Detector

Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by $\sim$2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors.Code is available at https://github.com/hyz-xmaster/VarifocalNet .

cs.CV↗

arXiv2021

IFoodCloud: A Platform for Real-time Sentiment Analysis of Public Opinion about Food Safety in China

The Internet contains a wealth of public opinion on food safety, including views on food adulteration, food-borne diseases, agricultural pollution, irregular food distribution, and food production issues. In order to systematically collect and analyse public opinion on food safety, we developed IFoodCloud, a platform for the real-time sentiment analysis of public opinion on food safety in China. It collects data from more than 3,100 public sources that can be used to explore public opinion trends, public sentiment, and regional attention differences of food safety incidents. At the same time, we constructed a sentiment classification model using multiple lexicon-based and deep learning-based algorithms integrated with IFoodCloud that provide an unprecedented rapid means of understanding the public sentiment toward specific food safety incidents. Our best model's F1-score achieved 0.9737. Further, three real-world cases are presented to demonstrate the application and robustness. IFoodCloud could be considered a valuable tool for promote scientisation of food safety supervision and risk communication.

cs.CL↗

arXiv2020

The Robotic Vision Scene Understanding Challenge

Being able to explore an environment and understand the location and type of all objects therein is important for indoor robotic platforms that must interact closely with humans. However, it is difficult to evaluate progress in this area due to a lack of standardized testing which is limited due to the need for active robot agency and perfect object ground-truth. To help provide a standard for testing scene understanding systems, we present a new robot vision scene understanding challenge using simulation to enable repeatable experiments with active robot agency. We provide two challenging task types, three difficulty levels, five simulated environments and a new evaluation measure for evaluating 3D cuboid object maps. Our aim is to drive state-of-the-art research in scene understanding through enabling evaluation and comparison of active robotic vision systems.

cs.RO↗

arXiv2020

BenchBot: Evaluating Robotics Research in Photorealistic 3D Simulation and on Real Robots

We introduce BenchBot, a novel software suite for benchmarking the performance of robotics research across both photorealistic 3D simulations and real robot platforms. BenchBot provides a simple interface to the sensorimotor capabilities of a robot when solving robotics research problems; an interface that is consistent regardless of whether the target platform is simulated or a real robot. In this paper we outline the BenchBot system architecture, and explore the parallels between its user-centric design and an ideal research development process devoid of tangential robot engineering challenges. The paper describes the research benefits of using the BenchBot system, including: enhanced capacity to focus solely on research problems, direct quantitative feedback to inform research development, tools for deriving comprehensive performance characteristics, and submission formats which promote sharability and repeatability of research outcomes. BenchBot is publicly available (http://benchbot.org), and we encourage its use in the research community for comprehensively evaluating the simulated and real world performance of novel robotic algorithms.

cs.RO↗

arXiv2020

Stochastic Computing Implemented by Skyrmionic Logic Devices

Magnetic skyrmion, topologically non-trivial spin texture, has been considered as promising information carrier in future electronic devices because of its nanoscale size, low depinning current density and high motion velocity. Despite the broad interests in skyrmion racetrack memory, researchers have been recently exploiting logic functions enabled by using the particle-like behaviors of skyrmions. These functions can be applied to unconventional computing, such as stochastic computing (SC), which treats data as probabilities and is superior to binary computing due to its simplicity of logic operation. In this work, we demonstrate SC implemented by skyrmionic logic devices. We propose a skyrmionic AND-OR logic device as a multiplier in the stochastic domain and two skyrmionic multiplexer (MUX) logic devices as stochastic adders. With the assist of voltage controlled magnetic anisotropy (VCMA), the precise control of skyrmions collision is not required in the skyrmionic AND-OR logic device, thus improving the operation robustness. In the two MUX logic devices, skyrmions can be driven by Zhang-Li torque or spin orbit torque (SOT). Particularly, we can flexibly regulate the skyrmion motion by VCMA or voltage controlled Dzyaloshinskii-Moriya Interaction (VCDMI) in the SOT case. Furthermore, 3-bit stochastic multiplier and adder are demonstrated by micromagnetic simulations. In addition, simulations in synthetic antiferromagnets (SAF) show that the performance of our skyrmionic logic gates can be optimized through advanced materials. Our work opens up perspective to implement SC using skyrmionic logic devices.

physics.app-ph↗

arXiv2020

Enhanced Light-Matter Interactions in Dielectric Nanostructures via Machine Learning Approach

A key concept underlying the specific functionalities of metasurfaces, i.e. arrays of subwavelength nanoparticles, is the use of constituent components to shape the wavefront of the light, on-demand. Metasurfaces are versatile and novel platforms to manipulate the scattering, colour, phase or the intensity of the light. Currently, one of the typical approaches for designing a metasurface is to optimize one or two variables, among a vast number of fixed parameters, such as various materials' properties and coupling effects, as well as the geometrical parameters. Ideally, it would require a multi-dimensional space optimization through direct numerical simulations. Recently, an alternative approach became quite popular allowing to reduce the computational cost significantly based on a deep-learning-assisted method. In this paper, we utilize a deep-learning approach for obtaining high-quality factor (high-Q) resonances with desired characteristics, such as linewidth, amplitude and spectral position. We exploit such high-Q resonances for the enhanced light-matter interaction in nonlinear optical metasurfaces and optomechanical vibrations, simultaneously. We demonstrate that optimized metasurfaces lead up to 400+ folds enhancement of the third harmonic generation (THG); at the same time, they also contribute to 100+ folds enhancement in optomechanical vibrations. This approach can be further used to realize structures with unconventional scattering responses.

physics.optics↗

arXiv2020

Probabilistic Object Detection: Definition and Evaluation

We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections. Given the lack of methods capable of assessing such probabilistic object detections, we present the new Probability-based Detection Quality measure (PDQ).Unlike AP-based measures, PDQ has no arbitrary thresholds and rewards spatial and label quality, and foreground/background separation quality while explicitly penalising false positive and false negative detections. We contrast PDQ with existing mAP and moLRP measures by evaluating state-of-the-art detectors and a Bayesian object detector based on Monte Carlo Dropout. Our experiments indicate that conventional object detectors tend to be spatially overconfident and thus perform poorly on the task of probabilistic object detection. Our paper aims to encourage the development of new object detection approaches that provide detections with accurately estimated spatial and label uncertainties and are of critical importance for deployment on robots and embodied AI systems in the real world.

cs.CV↗