arXiv subjects

Yawen Zhang

Publications and source records attributed to Yawen Zhang.

29 records · Page 2Linked to original sources

arXiv2023

LOWA: Localize Objects in the Wild with Attributes

We present LOWA, a novel method for localizing objects with attributes effectively in the wild. It aims to address the insufficiency of current open-vocabulary object detectors, which are limited by the lack of instance-level attribute classification and rare class names. To train LOWA, we propose a hybrid vision-language training strategy to learn object detection and recognition with class names as well as attribute information. With LOWA, users can not only detect objects with class names, but also able to localize objects by attributes. LOWA is built on top of a two-tower vision-language architecture and consists of a standard vision transformer as the image encoder and a similar transformer as the text encoder. To learn the alignment between visual and text inputs at the instance level, we train LOWA with three training steps: object-level training, attribute-aware learning, and free-text joint training of objects and attributes. This hybrid training strategy first ensures correct object detection, then incorporates instance-level attribute information, and finally balances the object class and attribute sensitivity. We evaluate our model performance of attribute classification and attribute localization on the Open-Vocabulary Attribute Detection (OVAD) benchmark and the Visual Attributes in the Wild (VAW) dataset, and experiments indicate strong zero-shot performance. Ablation studies additionally demonstrate the effectiveness of each training step of our approach.

cs.CV↗

arXiv2022

Air Pollution Hotspot Detection and Source Feature Analysis using Cross-domain Urban Data

Air pollution is a major global environmental health threat, in particular for people who live or work near pollution sources. Areas adjacent to pollution sources often have high ambient pollution concentrations, and those areas are commonly referred to as air pollution hotspots. Detecting and characterizing pollution hotspots are of great importance for air quality management, but are challenging due to the high spatial and temporal variability of air pollutants. In this work, we explore the use of mobile sensing data (i.e., air quality sensors installed on vehicles) to detect pollution hotspots. One major challenge with mobile sensing data is uneven sampling, i.e., data collection can vary by both space and time. To address this challenge, we propose a two-step approach to detect hotspots from mobile sensing data, which includes local spike detection and sample-weighted clustering. Essentially, this approach tackles the uneven sampling issue by weighting samples based on their spatial frequency and temporal hit rate, so as to identify robust and persistent hotspots. To contextualize the hotspots and discover potential pollution source characteristics, we explore a variety of cross-domain urban data and extract features from them. As a soft-validation of the extracted features, we build hotspot inference models for cities with and without mobile sensing data. Evaluation results using real-world mobile sensing air quality data as well as cross-domain urban data demonstrate the effectiveness of our approach in detecting and inferring pollution hotspots. Furthermore, the empirical analysis of hotspots and source features yields useful insights regarding neighborhood pollution sources.

cs.LG↗

arXiv2020

Exploring the Usage of Online Food Delivery Data for Intra-Urban Job and Housing Mobility Detection and Characterization

Human mobility plays a critical role in urban planning and policy-making. However, at certain spatial and temporal resolutions, it is very challenging to track, for example, job and housing mobility. In this study, we explore the usage of a new modality of dataset, online food delivery data, to detect job and housing mobility. By leveraging millions of meal orders from a popular online food ordering and delivery service in Beijing, China, we are able to detect job and housing moves at much higher spatial and temporal resolutions than using traditional data sources. Popular moving seasons and origins/destinations can be well identified. More importantly, we match the detected moves to both macro- and micro-level factors so as to characterize job and housing dynamics. Our findings suggest that commuting distance is a major factor for job and housing mobility. We also observe that: (1) For home movers, there is a trade-off between lower housing cost and shorter commuting distance given the urban spatial structure; (2) For job hoppers, those who frequently work overtime are more likely to reduce their working hours by switching jobs. While this new modality of dataset has its limitations, we believe that ensemble approaches would be promising, where a mash-up of multiple datasets with different characteristic limitations can provide a more comprehensive picture of job and housing dynamics. Our work demonstrates the effectiveness of utilizing food delivery data to detect and analyze job and housing mobility, and contributes to realizing the full potential of ensemble-based approaches.

cs.CY↗

arXiv2020

A purely 3-D geometrical solution to Mathematics Magazine Problem 2065

We proposed a purely 3-D geometrical solution to Mathematics Magazine Problem 2065. Let $\mathcal{Q}$ be a cube centered at the origin of $\mathbb{R}^3$. Choose a unit vector $(a,b,c)$ uniformly at random on the surface of the unit sphere $a^2+b^2+c^2=1$, and let $Π$ be the plane $ax+by+cz=0$ through the origin and normal to $(a,b,c)$. What is the probability that the intersection of $Π$ with $\mathcal{Q}$ is a hexagon?

math.HO↗

arXiv2020

DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging

The state-of-the-art deep learning algorithms rely on distributed training systems to tackle the increasing sizes of models and training data sets. Minibatch stochastic gradient descent (SGD) algorithm requires workers to halt forward/back propagations, to wait for gradients aggregated from all workers, and to receive weight updates before the next batch of tasks. This synchronous execution model exposes the overheads of gradient/weight communication among a large number of workers in a distributed training system. We propose a new SGD algorithm, DaSGD (Local SGD with Delayed Averaging), which parallelizes SGD and forward/back propagations to hide 100% of the communication overhead. By adjusting the gradient update scheme, this algorithm uses hardware resources more efficiently and reduces the reliance on the low-latency and high-throughput inter-connects. The theoretical analysis and the experimental results show its convergence rate O(1/sqrt(K)), the same as SGD. The performance evaluation demonstrates it enables a linear performance scale-up with the cluster size.

cs.DC↗

arXiv2019

Learn Electronic Health Records by Fully Decentralized Federated Learning

Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network. In this paper, we focus on improving the communication efficiency for fully decentralized federated learning over a graph, where the algorithm performs local updates for several iterations and then enables communications among the nodes. In such a way, the communication rounds of exchanging the common interest of parameters can be saved significantly without loss of optimality of the solutions. Multiple numerical simulations based on large, real-world electronic health record databases showcase the superiority of the decentralized federated learning compared with classic methods.

cs.LG↗

arXiv2019

An Energy-Efficient Mixed-Signal Parallel Multiply-Accumulate (MAC) Engine Based on Stochastic Computing

Convolutional neural networks (CNN) have achieved excellent performance on various tasks, but deploying CNN to edge is constrained by the high energy consumption of convolution operation. Stochastic computing (SC) is an attractive paradigm which performs arithmetic operations with simple logic gates and low hardware cost. This paper presents an energy-efficient mixed-signal multiply-accumulate (MAC) engine based on SC. A parallel architecture is adopted in this work to solve the latency problem of SC. The simulation results show that the overall energy consumption of our design is 5.03pJ per 26-input MAC operation under 28nm CMOS technology.

eess.SP↗

arXiv2019

Memory System Designed for Multiply-Accumulate (MAC) Engine Based on Stochastic Computing

Convolutional neural network (CNN) achieves excellent performance on fascinating tasks such as image recognition and natural language processing at the cost of high power consumption. Stochastic computing (SC) is an attractive paradigm implemented in low power applications which performs arithmetic operations with simple logic and low hardware cost. However, conventional memory structure designed and optimized for binary computing leads to extra data conversion costs, which significantly decreases the energy efficiency. Therefore, a new memory system designed for SC-based multiply-accumulate (MAC) engine applied in CNN which is compatible with conventional memory system is proposed in this paper. As a result, the overall energy consumption of our new computing structure is 0.91pJ, which is reduced by 82.1% compared with the conventional structure, and the energy efficiency achieves 164.8 TOPS/W.

eess.SP↗

arXiv2019

A Parallel Bitstream Generator for Stochastic Computing

Stochastic computing (SC) presents high error tolerance and low hardware cost, and has great potential in applications such as neural networks and image processing. However, the bitstream generator, which converts a binary number to bitstreams, occupies a large area and energy consumption, thus weakening the superiority of SC. In this paper, we propose a novel technique for generating bitstreams in parallel, which needs only one clock for conversion and significantly reduces the hardware cost. Synthesis results demonstrate that the proposed parallel bitstream generator improves 2.5x area and 712x energy consumption.

cs.ET↗

arXiv2017

Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach

During summer, melt ponds have a significant influence on Arctic sea-ice albedo. The melt pond fraction (MPF) also has the ability to forecast the Arctic sea-ice in a certain period. It is important to retrieve accurate melt pond fraction (MPF) from satellite data for Arctic research. This paper proposes a satellite MPF retrieval model based on the multi-layer neural network, named MPF-NN. Our model uses multi-spectral satellite data as model input and MPF information from multi-site and multi-period visible imagery as prior knowledge for modeling. It can effectively model melt ponds evolution of different regions and periods over the Arctic. Evaluation results show that the MPF retrieved from MODIS data using the proposed model has an RMSE of 3.91% and a correlation coefficient of 0.73. The seasonal distribution of MPF is also consistent with previous results.

physics.ao-ph↗

arXiv2015

Suppression of two-body collisional loss in an ultracold gas via the Fano effect

The Fano effect (U. Fano, Phys. Rev. \textbf{15},1866 (1961) shows that an inelastic scattering process can be suppressed when the output channel (OC) is coupled to an isolated bound state. In this paper we investigate the application of this effect for the suppression of two-body collisional losses of ultracold atoms. The Fano effect is originally derived via a first-order perturbation treatment for coupling between the incident channel (IC) and the OC. We generalize the Fano effect to systems with arbitrarily strong IC--OC couplings. We analytically prove that, in a system with one IC and one OC, when the inter-atomic interaction potentials are real functions of the inter-atomic distance, the exact s-wave inelastic scattering amplitude can always be suppressed to \emph{zero} by coupling between the IC or the OC (or both of them) and an extra isolated bound state. We further show that when the low-energy inelastic collision between two ultracold atoms is suppressed by this effect, the real part of the elastic scattering length between the atoms is still possible to be much larger than the range of inter-atomic interaction.In addition, when open scattering channels are coupled to two bound states, with the help of the Fano effect, independent control of the elastic and inelastic scattering amplitudes of two ultracold atoms can be achieved. Possible experimental realizations of our scheme are also discussed.

cond-mat.quant-gas↗