arXiv subjects

Bo Yan

Publications and source records attributed to Bo Yan.

At least 91 records · Page 5Linked to original sources

arXiv2021

Stronger Baseline for Person Re-Identification

Person re-identification (re-ID) aims to identify the same person of interest across non-overlapping capturing cameras, which plays an important role in visual surveillance applications and computer vision research areas. Fitting a robust appearance-based representation extractor with limited collected training data is crucial for person re-ID due to the high expanse of annotating the identity of unlabeled data. In this work, we propose a Stronger Baseline for person re-ID, an enhancement version of the current prevailing method, namely, Strong Baseline, with tiny modifications but a faster convergence rate and higher recognition performance. With the aid of Stronger Baseline, we obtained the third place (i.e., 0.94 in mAP) in 2021 VIPriors Re-identification Challenge without the auxiliary of ImageNet-based pre-trained parameter initialization and any extra supplemental dataset.

cs.CV↗

arXiv2021

The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge

The Visual Inductive Priors(VIPriors) for Data-Efficient Computer Vision challenges ask competitors to train models from scratch in a data-deficient setting. In this paper, we introduce the technical details of our submission to the ICCV2021 VIPriors instance segmentation challenge. Firstly, we designed an effective data augmentation method to improve the problem of data-deficient. Secondly, we conducted some experiments to select a proper model and made some improvements for this task. Thirdly, we proposed an effective training strategy which can improve the performance. Experimental results demonstrate that our approach can achieve a competitive result on the test set. According to the competition rules, we do not use any external image or video data and pre-trained weights. The implementation details above are described in section 2 and section 3. Finally, our approach can achieve 40.2\%AP@0.50:0.95 on the test set of ICCV2021 VIPriors instance segmentation challenge.

cs.CV↗

arXiv2021

A Gross-Pitaevskii-equation description of the momentum-state lattice: roles of the trap and many-body interactions

We report a theoretical description of the synthetic momentum-state lattices with a 3D Gross-Pitaevskii equation (GPE), where both the external trap potential and the mean-field spatial-density-dependent many-body interactions are naturally included and exactly treated. The GPE models exhibit better performance than the tight-binding model to depict the experimental observations. Since the trap modifies the dispersion relation for free particles and shapes the spatial density distribution that leads to inhomogeneous interactions, decoherences (damping oscillation) appear even for a short-time evolution. Our parametric calculations for the two-state oscillation suggest that we should work with a relatively shallow trap in the weakly interacting regime, especially when the long-term dynamics are concerned. The impact of the mean-field interaction, i.e., the self-trapping behavior, on the transport dynamics and the topological phase transition in a finite multiple-state lattice chain is also specifically investigated. Such an accurate treatment of the inhomogeneous interactions allows for further investigations on the interplay with disorder, the pair correlation dynamics, and the thermalization process in momentum space.

cond-mat.quant-gas↗

arXiv2021

Isotope Separation of Potassium with a magneto-optical combined method

Due to the similar physical and chemical properties, isotopes are usually hard to separate. On the other hand, the isotope shifts are very well separated in a high-resolution spectrum, making them possible to be addressed individually by lasers, thus separated. Here we report such an isotope separation experiment with Potassium atoms. The isotopes are independently optical pumped to the desired spin states, and then separated with a Stern-Gerlach scheme. A micro-capillary oven is used to collimate the atomic beam, and a Halbach-type magnet array is used to deflect the desired atoms. Finally, the $^{40}$K is enriched by two orders of magnitude. This magneto-optical combined method provides an effective way to separate isotopes and can be extended to other elements if the relevant optical pumping scheme is feasible.

physics.atom-ph↗

arXiv2021

Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

Almost all statements in knowledge bases have a temporal scope during which they are valid. Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement \textit{may} be associated with a temporal scope, has attracted growing attention. Prior works assume that each statement in a TKB \textit{must} be associated with a temporal scope. This ignores the fact that the scoping information is commonly missing in a KB. Thus prior work is typically incapable of handling generic use cases where a TKB is composed of temporal statements with/without a known temporal scope. In order to address this issue, we establish a new knowledge base embedding framework, called TIME2BOX, that can deal with atemporal and temporal statements of different types simultaneously. Our main insight is that answers to a temporal query always belong to a subset of answers to a time-agnostic counterpart. Put differently, time is a filter that helps pick out answers to be correct during certain periods. We introduce boxes to represent a set of answer entities to a time-agnostic query. The filtering functionality of time is modeled by intersections over these boxes. In addition, we generalize current evaluation protocols on time interval prediction. We describe experiments on two datasets and show that the proposed method outperforms state-of-the-art (SOTA) methods on both link prediction and time prediction.

cs.AI↗

arXiv2021

GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series

Traffic forecasting is an integral part of intelligent transportation systems (ITS). Achieving a high prediction accuracy is a challenging task due to a high level of dynamics and complex spatial-temporal dependency of road networks. For this task, we propose Graph Attention-Convolution-Attention Networks (GACAN). The model uses a novel Att-Conv-Att (ACA) block which contains two graph attention layers and one spectral-based GCN layer sandwiched in between. The graph attention layers are meant to capture temporal features while the spectral-based GCN layer is meant to capture spatial features. The main novelty of the model is the integration of time series of four different time granularities: the original time series, together with hourly, daily, and weekly time series. Unlike previous work that used multi-granularity time series by handling every time series separately, GACAN combines the outcome of processing all time series after each graph attention layer. Thus, the effects of different time granularities are integrated throughout the model. We perform a series of experiments on three real-world datasets. The experimental results verify the advantage of using multi-granularity time series and that the proposed GACAN model outperforms the state-of-the-art baselines.

cs.LG↗

arXiv2021

Feature Pyramid Network for Multi-task Affective Analysis

Affective Analysis is not a single task, and the valence-arousal value, expression class, and action unit can be predicted at the same time. Previous researches did not pay enough attention to the entanglement and hierarchical relation of these three facial attributes. We propose a novel model named feature pyramid networks for multi-task affect analysis. The hierarchical features are extracted to predict three labels and we apply a teacher-student training strategy to learn from pretrained single-task models. Extensive experiment results demonstrate the proposed model outperforms other models. This is a submission to The 2nd Workshop and Competition on Affective Behavior Analysis in the wild (ABAW). The code and model are available for research purposes at https://github.com/ryanhe312/ABAW2-FPNMAA.

cs.CV↗

arXiv2021

Observation of topological phase with critical localization in a quasi-periodic lattice

Disorder and localization have dramatic influence on the topological properties of a quantum system. While strong disorder can close the band gap thus depriving topological materials of topological features, disorder may also induce topology from trivial band structures, wherein topological invariants are shared by completely localized states in real space. Here we experimentally investigate a fundamentally distinct scenario where a topological phase is identified in a critically localized regime, with eigenstates neither fully extended nor completely localized. Adopting the technique of momentum-lattice engineering for ultracold atoms, we implement a one-dimensional, generalized Aubry-André model with off-diagonal quasi-periodic disorder in momentum space, and characterize its localization and topological properties through dynamic observables. We then demonstrate the impact of interactions on the critically localized topological state, as a first experimental endeavour toward the clarification of many-body critical phase, the critical analogue of the many-body localized state.

cond-mat.quant-gas↗

arXiv2021

DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by leveraging Convolutional Neural Networks (CNNs) to focus on different quadrants of optical flow input. To enhance the ability of feature selection, we further introduce an effective channel-spatial attention mechanism to force each branch to explicitly distill related information for specific Frame to Frame (F2F) motion estimation. Experiments on various datasets involving outdoor driving and indoor walking scenarios show that the proposed DeepAVO outperforms the state-of-the-art monocular methods by a large margin, demonstrating competitive performance to the stereo VO algorithm and verifying promising potential for generalization.

cs.CV↗

arXiv2021

Exploring noise-induced chaos and complexity in a red blood cell system

We investigate dynamical changes and its corresponding phase space complexity in a stochastic red blood cell system. The system is obtained by incorporating power noise with the associated sinusoidal flow. Both chaotic and non-chaotic dynamics of sinusoidal flow in red blood cell are identified by 0-1 test. Furthermore, dynamical complexity of the sinusoidal flow in the system is investigated by heterogeneous recurrence based entropy. The numerical simulation is performed to quantify the existence of chaotic dynamics and complexity for the sinusoidal blood flow.

nlin.CD↗

arXiv2020

Generator Pyramid for High-Resolution Image Inpainting

Inpainting high-resolution images with large holes challenges existing deep learning based image inpainting methods. We present a novel framework -- PyramidFill for high-resolution image inpainting task, which explicitly disentangles content completion and texture synthesis. PyramidFill attempts to complete the content of unknown regions in a lower-resolution image, and synthesis the textures of unknown regions in a higher-resolution image, progressively. Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image. Since completing contents and synthesising textures demand different abilities from generators, we customize different architectures for the content GAN and texture GAN. Experiments on multiple datasets including CelebA-HQ, Places2 and a new natural scenery dataset (NSHQ) with different resolutions demonstrate that PyramidFill generates higher-quality inpainting results than the state-of-the-art methods. To better assess high-resolution image inpainting methods, we will release NSHQ, high-quality natural scenery images with high-resolution 1920$\times$1080.

cs.CV↗

arXiv2020

Periodic driving induced helical Floquet channels with ultracold atoms in momentum space

Employing the external degrees of freedom of atoms as synthetic dimensions renders easy and new accesses to quantum engineering and quantum simulation. As a recent development, ultracold atoms suffering from two-photon Bragg transitions can be diffracted into a series of discrete momentum states to form a momentum lattice. Here we provide a detailed analysis on such a system, and, as a concrete example, report the observation of robust helical Floquet channels, by introducing periodic driving sequences. The robustness of these channels against perturbations is confirmed, as a test for their topological origin captured by Floquet winding numbers. The periodic switching demonstrated here serves as a testbed for more complicated Floquet engieering schemes, and offers exciting opportunities to study novel topological physics in a many-body setting with tunable interactions.

cond-mat.quant-gas↗

arXiv2020

Quantum Zeno effects across a parity-time symmetry breaking transition in atomic momentum space

We experimentally study quantum Zeno effects in a parity-time (PT) symmetric cold atom gas periodically coupled to a reservoir. Based on the state-of-the-art control of inter-site couplings of atoms in a momentum lattice, we implement a synthetic two-level system with passive PT symmetry over two lattice sites, where an effective dissipation is introduced through repeated couplings to the rest of the lattice. Quantum Zeno (anti-Zeno) effects manifest in our experiment as the overall dissipation of the two-level system becoming suppressed (enhanced) with increasing coupling intensity or frequency. We demonstrate that quantum Zeno regimes exist in the broken PT symmetry phase, and are bounded by exceptional points separating the PT symmetric and PT broken phases, as well as by a discrete set of critical coupling frequencies. Our experiment establishes the connection between PT-symmetry-breaking transitions and quantum Zeno effects, and is extendable to higher dimensions or to interacting regimes, thanks to the flexible control with atoms in a momentum lattice.

cond-mat.quant-gas↗

arXiv2020

Isometric Graph Neural Networks

Many tasks that rely on representations of nodes in graphs would benefit if those representations were faithful to distances between nodes in the graph. Geometric techniques to extract such representations have poor scaling over large graph size, and recent advances in Graph Neural Network (GNN) algorithms have limited ability to reflect graph distance information beyond the first degree neighborhood. To enable this highly desired capability, we propose a technique to learn Isometric Graph Neural Networks (IGNN), which requires changing the input representation space and loss function to enable any GNN algorithm to generate representations that reflect distances between nodes. We experiment with the isometric technique on several GNN architectures for modeling multiple prediction tasks on multiple datasets. In addition to an improvement in AUC-ROC as high as $43\%$ in these experiments, we observe a consistent and substantial improvement as high as 400% in Kendall's Tau (KT), a measure that directly reflects distance information, demonstrating that the learned embeddings do account for graph distances.

cs.LG↗

arXiv2020

SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting

Learning knowledge graph (KG) embeddings is an emerging technique for a variety of downstream tasks such as summarization, link prediction, information retrieval, and question answering. However, most existing KG embedding models neglect space and, therefore, do not perform well when applied to (geo)spatial data and tasks. For those models that consider space, most of them primarily rely on some notions of distance. These models suffer from higher computational complexity during training while still losing information beyond the relative distance between entities. In this work, we propose a location-aware KG embedding model called SE-KGE. It directly encodes spatial information such as point coordinates or bounding boxes of geographic entities into the KG embedding space. The resulting model is capable of handling different types of spatial reasoning. We also construct a geographic knowledge graph as well as a set of geographic query-answer pairs called DBGeo to evaluate the performance of SE-KGE in comparison to multiple baselines. Evaluation results show that SE-KGE outperforms these baselines on the DBGeo dataset for geographic logic query answering task. This demonstrates the effectiveness of our spatially-explicit model and the importance of considering the scale of different geographic entities. Finally, we introduce a novel downstream task called spatial semantic lifting which links an arbitrary location in the study area to entities in the KG via some relations. Evaluation on DBGeo shows that our model outperforms the baseline by a substantial margin.

cs.DB↗

arXiv2020

Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells

Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a strikingly similar situation in spatial analysis, which focuses on incorporating both absolute positions and spatial contexts of geographic objects such as POIs into models. A general-purpose representation model for space is valuable for a multitude of tasks. However, no such general model exists to date beyond simply applying discretization or feed-forward nets to coordinates, and little effort has been put into jointly modeling distributions with vastly different characteristics, which commonly emerges from GIS data. Meanwhile, Nobel Prize-winning Neuroscience research shows that grid cells in mammals provide a multi-scale periodic representation that functions as a metric for location encoding and is critical for recognizing places and for path-integration. Therefore, we propose a representation learning model called Space2Vec to encode the absolute positions and spatial relationships of places. We conduct experiments on two real-world geographic data for two different tasks: 1) predicting types of POIs given their positions and context, 2) image classification leveraging their geo-locations. Results show that because of its multi-scale representations, Space2Vec outperforms well-established ML approaches such as RBF kernels, multi-layer feed-forward nets, and tile embedding approaches for location modeling and image classification tasks. Detailed analysis shows that all baselines can at most well handle distribution at one scale but show poor performances in other scales. In contrast, Space2Vec's multi-scale representation can handle distributions at different scales.

cs.CV↗

arXiv2020

Tunable non-reciprocal quantum transport through a dissipative Aharonov-Bohm ring in ultracold atoms

We report the experimental observation of tunable, non-reciprocal quantum transport of a Bose-Einstein condensate in a momentum lattice. By implementing a dissipative Aharonov-Bohm (AB) ring in momentum space and sending atoms through it, we demonstrate a directional atom flow by measuring the momentum distribution of the condensate at different times. While the dissipative AB ring is characterized by the synthetic magnetic flux through the ring and the laser-induced loss on it, both the propagation direction and transport rate of the atom flow sensitively depend on these highly tunable parameters. We demonstrate that the non-reciprocity originates from the interplay of the synthetic magnetic flux and the laser-induced loss, which simultaneously breaks the inversion and the time-reversal symmetries. Our results open up the avenue for investigating non-reciprocal dynamics in cold atoms, and highlight the dissipative AB ring as a flexible building element for applications in quantum simulation and quantum information.

cond-mat.quant-gas↗

arXiv2020

Topological quantum walks in momentum space with a Bose-Einstein condensate

We report the experimental implementation of discrete-time topological quantum walks of a Bose-Einstein condensate in momentum space. Introducing stroboscopic driving sequences to the generation of a momentum lattice, we show that the dynamics of atoms along the lattice is effectively governed by a periodically driven Su-Schrieffer-Heeger model, which is equivalent to a discrete-time topological quantum walk. We directly measure the underlying topological invariants through time-averaged mean chiral displacements, which are consistent with our experimental observation of topological phase transitions. We then observe interaction-induced localization in the quantum-walk dynamics, where atoms tend to populate a single momentum-lattice site under interactions that are non-local in momentum space. Our experiment opens up the avenue of investigating discrete-time topological quantum walks using cold atoms, where the many-body environment and tunable interactions offer exciting new possibilities.

cond-mat.quant-gas↗