arXiv subjects

Xin Ye

Publications and source records attributed to Xin Ye.

At least 55 records · Page 3Linked to original sources

arXiv2023

Computing Balanced Solutions for Large International Kidney Exchange Schemes

To overcome incompatibility issues, kidney patients may swap their donors. In international kidney exchange programmes (IKEPs), countries merge their national patient-donor pools. We consider a recently introduced credit system. In each round, countries are given an initial ``fair'' allocation of the total number of kidney transplants. This allocation is adjusted by a credit function yielding a target allocation. The goal is to find a solution that approaches the target allocation as closely as possible, to ensure long-term stability of the international pool. As solutions, we use maximum matchings that lexicographically minimize the country deviations from the target allocation. We perform, for the first time, a computational study for a {\it large} number of countries. For the initial allocations we use two easy-to-compute solution concepts, the benefit value and the contribution value, and four classical but hard-to-compute concepts, the Shapley value, nucleolus, Banzhaf value and tau value. By using state-of-the-art software we show that the latter four concepts are now within reach for IKEPs of up to fifteen countries. Our experiments show that using lexicographically minimal maximum matchings instead of ones that only minimize the largest deviation from the target allocation (as previously done) may make an IKEP up to 54% more balanced.

cs.GT↗

arXiv2022

From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)

Visual Indoor Navigation (VIN) task has drawn increasing attention from the data-driven machine learning communities especially with the recently reported success from learning-based methods. Due to the innate complexity of this task, researchers have tried approaching the problem from a variety of different angles, the full scope of which has not yet been captured within an overarching report. This survey first summarizes the representative work of learning-based approaches for the VIN task and then identifies and discusses lingering issues impeding the VIN performance, as well as motivates future research in these key areas worth exploring for the community.

cs.RO↗

arXiv2022

Good, Better, Best: Textual Distractors Generation for Multiple-Choice Visual Question Answering via Reinforcement Learning

Multiple-choice VQA has drawn increasing attention from researchers and end-users recently. As the demand for automatically constructing large-scale multiple-choice VQA data grows, we introduce a novel task called textual Distractors Generation for VQA (DG-VQA) focusing on generating challenging yet meaningful distractors given the context image, question, and correct answer. The DG-VQA task aims at generating distractors without ground-truth training samples since such resources are rarely available. To tackle the DG-VQA unsupervisedly, we propose Gobbet, a reinforcement learning(RL) based framework that utilizes pre-trained VQA models as an alternative knowledge base to guide the distractor generation process. In Gobbet, a pre-trained VQA model serves as the environment in RL setting to provide feedback for the input multi-modal query, while a neural distractor generator serves as the agent to take actions accordingly. We propose to use existing VQA models' performance degradation as indicators of the quality of generated distractors. On the other hand, we show the utility of generated distractors through data augmentation experiments, since robustness is more and more important when AI models apply to unpredictable open-domain scenarios or security-sensitive applications. We further conduct a manual case study on the factors why distractors generated by Gobbet can fool existing models.

cs.CV↗

arXiv2021

Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and overcomes the error propagation caused by ASR. End-to-end slot filling (SF) from speech is an essential component of end-to-end SLU, and is usually regarded as a sequence-to-sequence generation problem, heavily relied on the performance of language model of ASR. However, it is hard to generate a correct slot when the slot is out-of-vovabulary (OOV) in training data, especially when a slot is an anti-linguistic entity without grammatical rule. Inspired by object detection in computer vision that is to detect the object from an image, we consider SF as the task of slot detection from speech. In this paper, we formulate the SF task as a matching task and propose an end-to-end knowledge-based SF model, named Speech-to-Slot (Speech2Slot), to leverage knowledge to detect the boundary of a slot from the speech. We also release a large-scale dataset of Chinese speech for slot filling, containing more than 830,000 samples. The experiments show that our approach is markedly superior to the conventional pipeline SLU approach, and outperforms the state-of-the-art end-to-end SF approach with 12.51% accuracy improvement.

cs.CL↗

arXiv2021

Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph

We present a novel two-layer hierarchical reinforcement learning approach equipped with a Goals Relational Graph (GRG) for tackling the partially observable goal-driven task, such as goal-driven visual navigation. Our GRG captures the underlying relations of all goals in the goal space through a Dirichlet-categorical process that facilitates: 1) the high-level network raising a sub-goal towards achieving a designated final goal; 2) the low-level network towards an optimal policy; and 3) the overall system generalizing unseen environments and goals. We evaluate our approach with two settings of partially observable goal-driven tasks -- a grid-world domain and a robotic object search task. Our experimental results show that our approach exhibits superior generalization performance on both unseen environments and new goals.

cs.CV↗

arXiv2021

Efficient Robotic Object Search via HIEM: Hierarchical Policy Learning with Intrinsic-Extrinsic Modeling

Despite the significant success at enabling robots with autonomous behaviors makes deep reinforcement learning a promising approach for robotic object search task, the deep reinforcement learning approach severely suffers from the nature sparse reward setting of the task. To tackle this challenge, we present a novel policy learning paradigm for the object search task, based on hierarchical and interpretable modeling with an intrinsic-extrinsic reward setting. More specifically, we explore the environment efficiently through a proxy low-level policy which is driven by the intrinsic rewarding sub-goals. We further learn our hierarchical policy from the efficient exploration experience where we optimize both of our high-level and low-level policies towards the extrinsic rewarding goal to perform the object search task well. Experiments conducted on the House3D environment validate and show that the robot, trained with our model, can perform the object search task in a more optimal and interpretable way.

cs.RO↗

arXiv2020

Observation of resonant dipolar collisions in ultracold $^{23}$Na$^{87}$Rb rotational mixtures

We report the investigation on dipolar collisions in rotational state mixtures of ultracold bosonic $^{23}$Na$^{87}$Rb molecules. The large resonant dipole-dipole interaction between molecules in rotational states of opposite parities brings about significant modifications to their collisions, even when an electric field is not present. In this work, this effect is revealed by measuring the dramatically enhanced two-body loss rate constants in the mixtures. In addition, the dipolar interaction strength can be tuned by preparing the NaRb mixture in different rotational levels with microwave spectroscopy. When the rotational level combination is not of the lowest energy, contributions from hyperfine changing collisions are also observed. Our measured loss rate constants are in good agreement with a quantum close-coupling calculation which we also present in full detail.

physics.atom-ph↗

arXiv2020

Anisotropic Polarizability of Ultracold Ground-state $^{23}$Na$^{87}$Rb Molecules

We report measurements of the ac polarizabilities of ultracold ground-state $^{23}\rm{Na}^{87}\rm{Rb}$ molecules. While the polarizability of the ground rotational state $J = 0$ is isotropic, that of the first excited rotational state $J = 1$ is anisotropic and depends strongly on the light polarization angle. We obtain both polarizabilities precisely by combining trap oscillation frequency measurement and high resolution rotational spectroscopy driven by microwave. With the optimized light polarization angle and intensity combination, the nonuniformity of the differential ac Stark shift between the two rotational states is minimized and the rotational coherence time is observed to be the longest.

physics.atom-ph↗

arXiv2020

High efficient metasurface quarter-wave plate with wavefront engineering

Metasurfaces with local phase tuning by subwavelength elements promise unprecedented possibilities for ultra-thin and multifunctional optical devices, in which geometric phase design is widely used due to its resonant-free and large tolerance in fabrications. By arranging the orientations of anisotropic nano-antennas, the geometric phase-based metasurfaces can convert the incident spin light to its orthogonal state, and enable flexible wavefront engineering together with the function of a half-wave plate. Here, by incorporating the propagation phase, we realize another important optical device of quarter-wave plate together with the wavefront engineering as well, which is implemented by controlling both the cross- and co-polarized light simultaneously with a singlet metasurface. Highly efficient conversion of the spin light to a variety of linearly polarized light are obtained for meta-holograms, metalens focusing and imaging in blue light region. Our work provides a new strategy for efficient metasurfaces with both phase and polarization control, and enriches the functionalities of metasurface devices for wider application scenarios.

physics.optics↗

arXiv2019

AIM 2019 Challenge on Image Demoireing: Methods and Results

This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. This paper describes the challenge, and focuses on the proposed solutions and their results. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. A new dataset, called LCDMoire was created for this challenge, and consists of 10,200 synthetically generated image pairs (moire and clean ground truth). The challenge was divided into 2 tracks. Track 1 targeted fidelity, measuring the ability of demoire methods to obtain a moire-free image compared with the ground truth, while Track 2 examined the perceptual quality of demoire methods. The tracks had 60 and 39 registered participants, respectively. A total of eight teams competed in the final testing phase. The entries span the current the state-of-the-art in the image demoireing problem.

eess.IV↗

arXiv2019

Reachability Analysis of Self Modifying Code

A Self modifying code is code that modifies its own instructions during execution time. It is nowadays widely used, especially in malware to make the code hard to analyse and to detect by anti-viruses. Thus, the analysis of such self modifying programs is a big challenge. Pushdown systems (PDSs) is a natural model that is extensively used for the analysis of sequential programs because they allow to accurately model procedure calls and mimic the program's stack. In this work, we propose to extend the PushDown System model with self-modifying rules. We call the new model Self-Modifying PushDown System (SM-PDS). A SM-PDS is a PDS that can modify its own set of transitions during execution. We show how SM-PDSs can be used to naturally represent self-modifying programs and provide efficient algorithms to compute the backward and forward reachable configurations of SM-PDSs. We implemented our techniques in a tool and obtained encouraging results. In particular, we successfully applied our tool for the detection of self-modifying malware.

cs.FL↗

arXiv2019

LTL Model Checking of Self Modifying Code

Self modifying code is code that can modify its own instructions during the execution of the program. It is extensively used by malware writers to obfuscate their malicious code. Thus, analysing self modifying code is nowadays a big challenge. In this paper, we consider the LTL model-checking problem of self modifying code. We model such programs using self-modifying pushdown systems (SM-PDS), an extension of pushdown systems that can modify its own set of transitions during execution. We reduce the LTL model-checking problem to the emptiness problem of self-modifying Büchi pushdown systems (SM-BPDS). We implemented our techniques in a tool that we successfully applied for the detection of several self-modifying malware. Our tool was also able to detect several malwares that well-known antiviruses such as BitDefender, Kinsoft, Avira, eScan, Kaspersky, Qihoo-360, Baidu, Avast, and Symantec failed to detect.

cs.LO↗

arXiv2019

Observation of resonant scattering between ultracold heteronuclear Feshbach molecules

We report the observation of a dimer-dimer inelastic collision resonance for ultracold Feshbach molecules made of bosonic sodium and rubidium atoms. This resonance, which we attribute to the crossing of the dimer-dimer threshold with a heteronuclear tetramer state, manifests itself as a pronounced inelastic loss peak of dimers when the interspecies scattering length between the constituent atoms is tuned. Near this resonance, a strong modification of the temperature dependence of the dimer-dimer scattering is observed. Our result provides insight into the heteronuclear four-body system consisting of heavy and light bosons and offers the possibility of investigating ultracold molecules with tunable interactions.

cond-mat.quant-gas↗

arXiv2019

Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance

The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose their performance in the old tasks after training for new tasks. In this paper, we introduce an ensemble method of incremental classifier to alleviate this problem, which is based on the cosine distance between the output feature and the pre-defined center, and can let each task to be preserved in different networks. During training, we make use of PEDCC-Loss to train the CNN network. In the stage of testing, the prediction is determined by the cosine distance between the network latent features and pre-defined center. The experimental results on EMINST and CIFAR100 show that our method outperforms the recent LwF method, which use the knowledge distillation, and iCaRL method, which keep some old samples while training for new task. The method can achieve the goal of not forgetting old knowledge while training new classes, and solve the problem of catastrophic forgetting better.

cs.LG↗

arXiv2019

A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids

With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results in pattern recognition, image classification, object detection and tracking. For CNNs used for image classification, in addition to the network structure, more and more research is now focusing on the improvement of the loss function, so as to enlarge the inter-class feature differences, and reduce the intra-class feature variations as soon as possible. Besides the traditional Softmax, typical loss functions include L-Softmax, AM-Softmax, ArcFace, and Center loss, etc. Based on the concept of predefined evenly-distributed class centroids (PEDCC) in CSAE network, this paper proposes a PEDCC-based loss function called PEDCC-Loss, which can make the inter-class distance maximal and intra-class distance small enough in hidden feature space. Multiple experiments on image classification and face recognition have proved that our method achieve the best recognition accuracy, and network training is stable and easy to converge. Code is available in https://github.com/ZLeopard/PEDCC-Loss

cs.CV↗

arXiv2019

Analytical low-rank compression via proxy point selection

It has been known in potential theory that, for some kernels matrices corresponding to well-separated point sets, fast analytical low-rank approximation can be achieved via the use of proxy points. This proxy point method gives a surprisingly convenient way of explicitly writing out approximate basis matrices for a kernel matrix. However, this elegant strategy is rarely known or used in the numerical linear algebra community. It still needs clear algebraic understanding of the theoretical background. Moreover, rigorous quantifications of the approximation errors and reliable criteria for the selection of the proxy points are still missing. In this work, we use contour integration to clearly justify the idea in terms of a class of important kernels. We further provide comprehensive accuracy analysis for the analytical compression and show how to choose nearly optimal proxy points. The analytical compression is then combined with fast rank-revealing factorizations to get compact low-rank approximations and also to select certain representative points. We provide the error bounds for the resulting overall low-rank approximation. This work thus gives a fast and reliable strategy for compressing those kernel matrices. Furthermore, it provides an intuitive way of understanding the proxy point method and bridges the gap between this useful analytical strategy and practical low-rank approximations. Some numerical examples help to further illustrate the ideas.

math.NA↗

arXiv2019

GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environment

We study the problem of learning a generalizable action policy for an intelligent agent to actively approach an object of interest in an indoor environment solely from its visual inputs. While scene-driven or recognition-driven visual navigation has been widely studied, prior efforts suffer severely from the limited generalization capability. In this paper, we first argue the object searching task is environment dependent while the approaching ability is general. To learn a generalizable approaching policy, we present a novel solution dubbed as GAPLE which adopts two channels of visual features: depth and semantic segmentation, as the inputs to the policy learning module. The empirical studies conducted on the House3D dataset as well as on a physical platform in a real world scenario validate our hypothesis, and we further provide in-depth qualitative analysis.

cs.RO↗

arXiv2018

Dipolar Collisions of Ultracold Ground-state Bosonic Molecules

The dipolar collision between ultracold polar molecules is an important topic both by its own right from the fundamental point of view and for the successful exploration of many-body physics with strong and long-range dipolar interactions. Here, we report the investigation of collisions between ultracold ground-state sodium-rubidium molecules in electric fields with induced electric dipole moments as large as 0.7$\;$D. We observe a step-wise enhancement of losses due to the coupling between different partial waves induced by the increasingly stronger anisotropic dipolar interactions. Varying the temperature of our sample, we find good agreement with theoretical loss rates assuming complex formation as the main loss process. Our results shed new light on the understanding of complex molecular collisions in the presence of strong dipolar interactions and also demonstrate the versatility of modifying molecular interactions with electric fields.

cond-mat.quant-gas↗