arXiv subjects

Junbo Zhang

Publications and source records attributed to Junbo Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2023

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT.

cs.CV↗

arXiv2022

Language-Assisted 3D Feature Learning for Semantic Scene Understanding

Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an end-to-end trained 3D scene understanding network. To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions. Given some free-form descriptions paired with 3D scenes, we extract the knowledge regarding the object relationships and object attributes. We then inject the knowledge to 3D feature learning through three classification-based auxiliary tasks. This language-assisted training can be combined with modern object detection and instance segmentation methods to promote 3D semantic scene understanding, especially in a label-deficient regime. Moreover, the 3D feature learned with language assistance is better aligned with the language features, which can benefit various 3D-language multimodal tasks. Experiments on several benchmarks of 3D-only and 3D-language tasks demonstrate the effectiveness of our language-assisted 3D feature learning. Code is available at https://github.com/Asterisci/Language-Assisted-3D.

cs.CV↗

arXiv2022

AirFormer: Predicting Nationwide Air Quality in China with Transformers

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

eess.SP↗

arXiv2022

An empirical study of weakly supervised audio tagging embeddings for general audio representations

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech and sound domains. Specifically, we benchmark weakly supervised pre-trained models (MobileNetV2 and EfficientNet-B0) against modern self-supervised learning methods (BYOL-A) as feature extractors. Fourteen downstream tasks are used for evaluation ranging from music instrument classification to language classification. Our results indicate that AT pre-trained models are an excellent transfer learning choice for music, event, and emotion recognition tasks. Further, finetuning AT models can also benefit speech-related tasks such as keyword spotting and intent classification.

cs.SD↗

arXiv2022

UniKW-AT: Unified Keyword Spotting and Audio Tagging

Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict a label (keyword in KWS, sound event in AT) for some fixed-sized input audio segment. This work proposes UniKW-AT: An initial approach for jointly training both KWS and AT. UniKW-AT enhances the noise-robustness for KWS, while also being able to predict specific sound events and enabling conditional wake-ups on sound events. Our approach extends the AT pipeline with additional labels describing the presence of a keyword. Experiments are conducted on the Google Speech Commands V1 (GSCV1) and the balanced Audioset (AS) datasets. The proposed MobileNetV2 model achieves an accuracy of 97.53% on the GSCV1 dataset and an mAP of 33.4 on the AS evaluation set. Further, we show that significant noise-robustness gains can be observed on a real-world KWS dataset, greatly outperforming standard KWS approaches. Our study shows that KWS and AT can be merged into a single framework without significant performance degradation.

cs.SD↗

arXiv2022

HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting

Weather Forecasting is an attractive challengeable task due to its influence on human life and complexity in atmospheric motion. Supported by massive historical observed time series data, the task is suitable for data-driven approaches, especially deep neural networks. Recently, the Graph Neural Networks (GNNs) based methods have achieved excellent performance for spatio-temporal forecasting. However, the canonical GNNs-based methods only individually model the local graph of meteorological variables per station or the global graph of whole stations, lacking information interaction between meteorological variables in different stations. In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations. An adaptive graph learning layer and spatial graph convolution are employed to construct self-learning graph and study hidden dependency among nodes of variable-level and station-level graph. For capturing temporal pattern, the dilated inception as the backbone of gate temporal convolution is designed to model long and various meteorological trends. Moreover, a dynamic interaction learning is proposed to build bidirectional information passing in hierarchical graph. Experimental results on three real-world meteorological datasets demonstrate the superior performance of HiSTGNN beyond 7 baselines and it reduces the errors by 4.2% to 11.6% especially compared to state-of-the-art weather forecasting method.

cs.LG↗

arXiv2022

Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings two drawbacks. First, the artificial choice of augmentation types brings specific representational invariances to the model, which have different degrees of positive and negative effects on different downstream tasks. Treating each type of augmentation equally during training makes the model learn non-optimal representations for various downstream tasks and limits the flexibility to choose augmentation types beforehand. Second, the strong data augmentations used in classic contrastive learning methods may bring too much invariance in some cases, and fine-grained information that is essential to some downstream tasks may be lost. This paper proposes a general method to alleviate these two problems by considering where and what to contrast in a general contrastive learning framework. We first propose to learn different augmentation invariances at different depths of the model according to the importance of each data augmentation instead of learning representational invariances evenly in the backbone. We then propose to expand the contrast content with augmentation embeddings to reduce the misleading effects of strong data augmentations. Experiments based on several baseline methods demonstrate that we learn better representations for various benchmarks on classification, detection, and segmentation downstream tasks.

cs.CV↗

arXiv2022

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

Data insufficiency problems (i.e., data missing and label scarcity) caused by inadequate services and infrastructures or imbalanced development levels of cities have seriously affected the urban computing tasks in real scenarios. Prior transfer learning methods inspire an elegant solution to the data insufficiency, but are only concerned with one kind of insufficiency issue and fail to give consideration to both sides. In addition, most previous cross-city transfer methods overlook inter-city data privacy which is a public concern in practical applications. To address the above challenging problems, we propose a novel Cross-city Federated Transfer Learning framework (CcFTL) to cope with the data insufficiency and privacy problems. Concretely, CcFTL transfers the relational knowledge from multiple rich-data source cities to the target city. Besides, the model parameters specific to the target task are firstly trained on the source data and then fine-tuned to the target city by parameter transfer. With our adaptation of federated training and homomorphic encryption settings, CcFTL can effectively deal with the data privacy problem among cities. We take the urban region profiling as an application of smart cities and evaluate the proposed method with a real-world study. The experiments demonstrate the notable superiority of our framework over several competitive state-of-the-art methods.

cs.LG↗

arXiv2022

Contrastive Deep Supervision

The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last layer and propagates the supervision layer-by-layer, which leads to hardship in optimizing the intermediate layers. Recently, deep supervision has been proposed to add auxiliary classifiers to the intermediate layers of deep neural networks. By optimizing these auxiliary classifiers with the supervised task loss, the supervision can be applied to the shallow layers directly. However, deep supervision conflicts with the well-known observation that the shallow layers learn low-level features instead of task-biased high-level semantic features. To address this issue, this paper proposes a novel training framework named Contrastive Deep Supervision, which supervises the intermediate layers with augmentation-based contrastive learning. Experimental results on nine popular datasets with eleven models demonstrate its effects on general image classification, fine-grained image classification and object detection in supervised learning, semi-supervised learning and knowledge distillation. Codes have been released in Github.

cs.CV↗

arXiv2022

Integrating a Manual Pipette into a Collaborative Robot Manipulator for Flexible Liquid Dispensing

This paper presents a system integration approach for a 6-DoF (Degree of Freedom) collaborative robot to operate a pipette for liquid dispensing. Its technical development is threefold. First, we designed an end-effector for holding and triggering manual pipettes. Second, we took advantage of a collaborative robot to recognize labware poses and planned robotic motion based on the recognized poses. Third, we developed vision-based classifiers to predict and correct positioning errors and thus precisely attached pipettes to disposable tips. Through experiments and analysis, we confirmed that the developed system, especially the planning and visual recognition methods, could help secure high-precision and flexible liquid dispensing. The developed system is suitable for low-frequency, high-repetition biochemical liquid dispensing tasks. We expect it to promote the deployment of collaborative robots for laboratory automation and thus improve the experimental efficiency without significantly customizing a laboratory environment.

cs.RO↗

arXiv2022

CHES: a space-borne astrometric mission for the detection of habitable planets of the nearby solar-type stars

The Closeby Habitable Exoplanet Survey (CHES) mission is proposed to discover habitable-zone Earth-like planets of the nearby solar-type stars ($\sim 10~\mathrm{pc}$ away from our solar system) via micro-arcsecond relative astrometry. The major scientific objectives of CHES are: to search for Earth Twins or terrestrial planets in habitable zones orbiting 100 FGK nearby stars; further to conduct a comprehensive survey and extensively characterize the nearby planetary systems. The primary payload is a high-quality, low-distortion, high-stability telescope. The optical subsystem is a coaxial three-mirror anastigmat (TMA) with a $1.2 \mathrm{~m}$-aperture, $0.44^{\circ} \times 0.44^{\circ}$ field of view and $500 \mathrm{~nm}-900 \mathrm{~nm}$ working waveband. The camera focal plane is composed of 81 MOSAIC scientific CMOS detectors each with $4 \mathrm{~K} \times 4 \mathrm{~K}$ pixels. The heterodyne laser interferometric calibration technology is employed to ensure micro-arcsecond level (1 $μ$as) relative astrometry precision to meet the requirements for detection of Earth-like planets. CHES satellite operates at the Sun-Earth L2 point and observes the entire target stars for 5 years. CHES will offer the first direct measurements of true masses and inclinations of Earth Twins and super-Earths orbiting our neighbor stars based on micro-arcsecond astrometry from space. This will definitely enhance our understanding of the formation of diverse nearby planetary systems and the emergence of other worlds for solar-type stars, and finally to reflect the evolution of our own solar system.

astro-ph.EP↗

arXiv2022

Pseudo strong labels for large scale weakly supervised audio tagging

Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual labeling cost. This work proposes pseudo strong labels (PSL), a simple label augmentation framework that enhances the supervision quality for large-scale weakly supervised audio tagging. A machine annotator is first trained on a large weakly supervised dataset, which then provides finer supervision for a student model. Using PSL we achieve an mAP of 35.95 balanced train subset of Audioset using a MobileNetV2 back-end, significantly outperforming approaches without PSL. An analysis is provided which reveals that PSL mitigates missing labels. Lastly, we show that models trained with PSL are also superior at generalizing to the Freesound datasets (FSD) than their weakly trained counterparts.

cs.SD↗

arXiv2022

Spatio-Temporal Dynamic Graph Relation Learning for Urban Metro Flow Prediction

Urban metro flow prediction is of great value for metro operation scheduling, passenger flow management and personal travel planning. However, it faces two main challenges. First, different metro stations, e.g. transfer stations and non-transfer stations, have unique traffic patterns. Second, it is challenging to model complex spatio-temporal dynamic relation of metro stations. To address these challenges, we develop a spatio-temporal dynamic graph relational learning model (STDGRL) to predict urban metro station flow. First, we propose a spatio-temporal node embedding representation module to capture the traffic patterns of different stations. Second, we employ a dynamic graph relationship learning module to learn dynamic spatial relationships between metro stations without a predefined graph adjacency matrix. Finally, we provide a transformer-based long-term relationship prediction module for long-term metro flow prediction. Extensive experiments are conducted based on metro data in Beijing, Shanghai, Chongqing and Hangzhou. Experimental results show the advantages of our method beyond 11 baselines for urban metro flow prediction.

cs.LG↗

arXiv2021

Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global inter-region dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework-Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on several real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines. Source codes of implementations are available at https://github.com/jill001/ST-GDN.

cs.LG↗

arXiv2021

POI Alias Discovery in Delivery Addresses using User Locations

People often refer to a place of interest (POI) by an alias. In e-commerce scenarios, the POI alias problem affects the quality of the delivery address of online orders, bringing substantial challenges to intelligent logistics systems and market decision-making. Labeling the aliases of POIs involves heavy human labor, which is inefficient and expensive. Inspired by the observation that the users' GPS locations are highly related to their delivery address, we propose a ubiquitous alias discovery framework. Firstly, for each POI name in delivery addresses, the location data of its associated users, namely Mobility Profile are extracted. Then, we identify the alias relationship by modeling the similarity of mobility profiles. Comprehensive experiments on the large-scale location data and delivery address data from JD logistics validate the effectiveness.

cs.SI↗

arXiv2021

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

cs.SD↗

arXiv2021

speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment

This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. A baseline system is released in open source to illustrate the phoneme-level pronunciation assessment workflow on this corpus. This corpus is allowed to be used freely for commercial and non-commercial purposes. It is available for free download from OpenSLR, and the corresponding baseline system is published in the Kaldi speech recognition toolkit.

cs.CL↗

arXiv2021

ASASSN-18am/SN 2018gk : An overluminous Type IIb supernova from a massive progenitor

ASASSN-18am/SN 2018gk is a newly discovered member of the rare group of luminous, hydrogen-rich supernovae (SNe) with a peak absolute magnitude of $M_V \approx -20$ mag that is in between normal core-collapse SNe and superluminous SNe. These SNe show no prominent spectroscopic signatures of ejecta interacting with circumstellar material (CSM), and their powering mechanism is debated. ASASSN-18am declines extremely rapidly for a Type II SN, with a photospheric-phase decline rate of $\sim6.0~\rm mag~(100 d)^{-1}$. Owing to the weakening of HI and the appearance of HeI in its later phases, ASASSN-18am is spectroscopically a Type IIb SN with a partially stripped envelope. However, its photometric and spectroscopic evolution show significant differences from typical SNe IIb. Using a radiative diffusion model, we find that the light curve requires a high synthesised $\rm ^{56}Ni$ mass $M_{\rm Ni} \sim0.4~M_\odot$ and ejecta with high kinetic energy $E_{\rm kin} = (7-10) \times10^{51} $ erg. Introducing a magnetar central engine still requires $M_{\rm Ni} \sim0.3~M_\odot$ and $E_{\rm kin}= 3\times10^{51} $ erg. The high $\rm ^{56}Ni$ mass is consistent with strong iron-group nebular lines in its spectra, which are also similar to several SNe Ic-BL with high $\rm ^{56}Ni$ yields. The earliest spectrum shows "flash ionisation" features, from which we estimate a mass-loss rate of $ \dot{M}\approx 2\times10^{-4}~\rm M_\odot~yr^{-1} $. This wind density is too low to power the luminous light curve by ejecta-CSM interaction. We measure expansion velocities as high as $ 17,000 $ km/s for $H_α$, which is remarkably high compared to other SNe II. We estimate an oxygen core mass of $1.8-3.4$ $M_\odot$ using the [OI] luminosity measured from a nebular-phase spectrum, implying a progenitor with a zero-age main sequence mass of $19-26$ $M_\odot$.

astro-ph.HE↗