arXiv subjects

Li Zhang

Publications and source records attributed to Li Zhang.

At least 631 records · Page 35Linked to original sources

arXiv2022

Correlated topological pumping of interacting bosons assisted by Bloch oscillations

Thouless pumping, not only achieving quantized transport but also immune to moderate disorder, has attracted growing attention in both experiments and theories. Here, we explore how particle-particle interactions affect topological transport in a periodically-modulated and tilted optical lattice. Not limited to wannier states, our scheme ensures a dispersionless quantized transport even for initial Gaussian-like wave packets of interacting bosons which do not uniformly occupy a given band. This is because the tilting potential leads to Bloch oscillations uniformly sampling the Berry curvatures over the entire Brillouin zone. The interplay among on-site potential difference, tunneling rate and interactions contributes to the topological transport of bound and scattering states and the topologically resonant tunnelings. Our study deepens the understanding of correlation effects on topological states, and provides a feasible way for detecting topological properties in interacting systems.

quant-ph↗

arXiv2022

A Preliminary Study on the Potential Usefulness of Open Domain Model for Missing Software Requirements Recommendation

Completeness is one of the most important attributes of software requirement specifications. Unfortunately, incompleteness is meanwhile one of the most difficult problems to detect. Some approaches have been proposed to detect missing requirements based on the requirement-oriented domain model. However, this kind of models are lacking for lots of domains. Fortunately, the domain models constructed for different purposes can usually be found online. This raises a question: whether or not these domain models are helpful in finding the missing functional information in requirement specification? To explore this question, we design and conduct a preliminary study by computing the overlapping rate between the entities in domain models and the concepts of natural language software requirements and then digging into four regularities of the occurrence of these entities(concepts) based on two example domains. The usefulness of these regularities, especially the one based on our proposed metric AHME (with F2 gains of 146% and 223% on the two domains than without any regularity), has been shown in experiments.

cs.SE↗

arXiv2022

Demonstration of broadband topological slow light

Slow-light devices are able to significantly enhance light-matter interaction due to the reduced group velocity of light, but a very low group velocity is usually achieved in a narrow bandwidth, accompanied by extreme sensitivity to imperfections that causes increased disorder-induced attenuation. Recent theories have suggested an ideal solution to this problem - unidirectional chiral photonic states, previously discovered in structures known as photonic topological insulators, not only resist backscattering from imperfections but can also be slowed down in the entire topological bandgap with multiple windings in the Brillouin zone. Here, we report on the experimental demonstration of broadband topological slow light in a photonic topological insulator. When coupled with periodic resonators that form flat bands, the chiral photonic states can wind many times around the Brillouin zone, achieving an ultra-low group velocity in the entire topological bandgap. This demonstration extends the scope of topological photonics into slow light engineering and opens a unique avenue in the dispersion manipulation of chiral photonic states.

physics.app-ph↗

arXiv2022

Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation

A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training paradigm, some competitive methods have sought to the latent-space information, which establishes the feature centroids (a.k.a prototypes) of the semantic classes and determines the pseudo label candidates by their distances from these centroids. In this paper, we argue that the latent space contains more information to be exploited thus taking one step further to capitalize on it. Firstly, instead of merely using the source-domain prototypes to determine the target pseudo labels as most of the traditional methods do, we bidirectionally produce the target-domain prototypes to degrade those source features which might be too hard or disturbed for the adaptation. Secondly, existing attempts simply model each category as a single and isotropic prototype while ignoring the variance of the feature distribution, which could lead to the confusion of similar categories. To cope with this issue, we propose to represent each category with multiple and anisotropic prototypes via Gaussian Mixture Model, in order to fit the de facto distribution of source domain and estimate the likelihood of target samples based on the probability density. We apply our method on GTA5->Cityscapes and Synthia->Cityscapes tasks and achieve 61.2 and 62.8 respectively in terms of mean IoU, substantially outperforming other competitive self-training methods. Noticeably, in some categories which severely suffer from the categorical confusion such as "truck" and "bus", our method achieves 56.4 and 68.8 respectively, which further demonstrates the effectiveness of our design.

cs.CV↗

arXiv2022

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields. However, the academic community still lacks a video dataset with diverse facial attribute annotations, which is crucial for the research on face-related videos. In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ). CelebV-HQ contains 35,666 video clips with the resolution of 512x512 at least, involving 15,653 identities. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion. We conduct a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality to demonstrate the diversity and temporal coherence of CelebV-HQ. Besides, its versatility and potential are validated on two representative tasks, i.e., unconditional video generation and video facial attribute editing. Furthermore, we envision the future potential of CelebV-HQ, as well as the new opportunities and challenges it would bring to related research directions. Data, code, and models are publicly available. Project page: https://celebv-hq.github.io.

cs.CV↗

arXiv2022

RCLane: Relay Chain Prediction for Lane Detection

Lane detection is an important component of many real-world autonomous systems. Despite a wide variety of lane detection approaches have been proposed, reporting steady benchmark improvements over time, lane detection remains a largely unsolved problem. This is because most of the existing lane detection methods either treat the lane detection as a dense prediction or a detection task, few of them consider the unique topologies (Y-shape, Fork-shape, nearly horizontal lane) of the lane markers, which leads to sub-optimal solution. In this paper, we present a new method for lane detection based on relay chain prediction. Specifically, our model predicts a segmentation map to classify the foreground and background region. For each pixel point in the foreground region, we go through the forward branch and backward branch to recover the whole lane. Each branch decodes a transfer map and a distance map to produce the direction moving to the next point, and how many steps to progressively predict a relay station (next point). As such, our model is able to capture the keypoints along the lanes. Despite its simplicity, our strategy allows us to establish new state-of-the-art on four major benchmarks including TuSimple, CULane, CurveLanes and LLAMAS.

cs.CV↗

arXiv2022

FashionViL: Fashion-Focused Vision-and-Language Representation Learning

Large-scale Vision-and-Language (V+L) pre-training for representation learning has proven to be effective in boosting various downstream V+L tasks. However, when it comes to the fashion domain, existing V+L methods are inadequate as they overlook the unique characteristics of both the fashion V+L data and downstream tasks. In this work, we propose a novel fashion-focused V+L representation learning framework, dubbed as FashionViL. It contains two novel fashion-specific pre-training tasks designed particularly to exploit two intrinsic attributes with fashion V+L data. First, in contrast to other domains where a V+L data point contains only a single image-text pair, there could be multiple images in the fashion domain. We thus propose a Multi-View Contrastive Learning task for pulling closer the visual representation of one image to the compositional multimodal representation of another image+text. Second, fashion text (e.g., product description) often contains rich fine-grained concepts (attributes/noun phrases). To exploit this, a Pseudo-Attributes Classification task is introduced to encourage the learned unimodal (visual/textual) representations of the same concept to be adjacent. Further, fashion V+L tasks uniquely include ones that do not conform to the common one-stream or two-stream architectures (e.g., text-guided image retrieval). We thus propose a flexible, versatile V+L model architecture consisting of a modality-agnostic Transformer so that it can be flexibly adapted to any downstream tasks. Extensive experiments show that our FashionViL achieves a new state of the art across five downstream tasks. Code is available at https://github.com/BrandonHanx/mmf.

cs.CV↗

arXiv2022

LAGOS-AND: A Large Gold Standard Dataset for Scholarly Author Name Disambiguation

In this paper, we present a method to automatically build large labeled datasets for the author ambiguity problem in the academic world by leveraging the authoritative academic resources, ORCID and DOI. Using the method, we built LAGOS-AND, two large, gold-standard datasets for author name disambiguation (AND), of which LAGOS-AND-BLOCK is created for clustering-based AND research and LAGOS-AND-PAIRWISE is created for classification-based AND research. Our LAGOS-AND datasets are substantially different from the existing ones. The initial versions of the datasets (v1.0, released in February 2021) include 7.5M citations authored by 798K unique authors (LAGOS-AND-BLOCK) and close to 1M instances (LAGOS-AND-PAIRWISE). And both datasets show close similarities to the whole Microsoft Academic Graph (MAG) across validations of six facets. In building the datasets, we reveal the variation degrees of last names in three literature databases, PubMed, MAG, and Semantic Scholar, by comparing author names hosted to the authors' official last names shown on the ORCID pages. Furthermore, we evaluate several baseline disambiguation methods as well as the MAG's author IDs system on our datasets, and the evaluation helps identify several interesting findings. We hope the datasets and findings will bring new insights for future studies. The code and datasets are publicly available.

cs.DL↗

arXiv2022

What Makes for Automatic Reconstruction of Pulmonary Segments

3D reconstruction of pulmonary segments plays an important role in surgical treatment planning of lung cancer, which facilitates preservation of pulmonary function and helps ensure low recurrence rates. However, automatic reconstruction of pulmonary segments remains unexplored in the era of deep learning. In this paper, we investigate what makes for automatic reconstruction of pulmonary segments. First and foremost, we formulate, clinically and geometrically, the anatomical definitions of pulmonary segments, and propose evaluation metrics adhering to these definitions. Second, we propose ImPulSe (Implicit Pulmonary Segment), a deep implicit surface model designed for pulmonary segment reconstruction. The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing. Compared with canonical segmentation methods, ImPulSe outputs continuous predictions of arbitrary resolutions with higher training efficiency and fewer parameters. Lastly, we experiment with different network inputs to analyze what matters in the task of pulmonary segment reconstruction. Our code is available at https://github.com/M3DV/ImPulSe.

eess.IV↗

arXiv2022

Device-centric Federated Analytics At Ease

Nowadays, high-volume and privacy-sensitive data are generated by mobile devices, which are better to be preserved on devices and queried on demand. However, data analysts still lack a uniform way to harness such distributed on-device data. In this paper, we propose a data querying system, Deck, that enables flexible device-centric federated analytics. The key idea of Deck is to bypass the app developers but allow the data analysts to directly submit their analytics code to run on devices, through a centralized query coordinator service. Deck provides a list of standard APIs to data analysts and handles most of the device-specific tasks underneath. Deck further incorporates two key techniques: (i) a hybrid permission checking mechanism and mandatory cross-device aggregation to ensure data privacy; (ii) a zero-knowledge statistical model that judiciously trades off query delay and query resource expenditure on devices. We fully implement Deck and plug it into 20 popular Android apps. An in-the-wild deployment on 1,642 volunteers shows that Deck significantly reduces the query delay by up to 30x compared to baselines. Our microbenchmarks also demonstrate that the standalone overhead of Deck is negligible.

cs.DC↗

arXiv2022

SiamMask: A Framework for Fast Online Object Tracking and Segmentation

In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the offline training procedure of popular fully-convolutional Siamese approaches by augmenting their losses with a binary segmentation task. Once the offline training is completed, SiamMask only requires a single bounding box for initialization and can simultaneously carry out visual object tracking and segmentation at high frame-rates. Moreover, we show that it is possible to extend the framework to handle multiple object tracking and segmentation by simply re-using the multi-task model in a cascaded fashion. Experimental results show that our approach has high processing efficiency, at around 55 frames per second. It yields real-time state-of-the-art results on visual-object tracking benchmarks, while at the same time demonstrating competitive performance at a high speed for video object segmentation benchmarks.

cs.CV↗

arXiv2022

Knowledge-aware Neural Collective Matrix Factorization for Cross-domain Recommendation

Cross-domain recommendation (CDR) can help customers find more satisfying items in different domains. Existing CDR models mainly use common users or mapping functions as bridges between domains but have very limited exploration in fully utilizing extra knowledge across domains. In this paper, we propose to incorporate the knowledge graph (KG) for CDR, which enables items in different domains to share knowledge. To this end, we first construct a new dataset AmazonKG4CDR from the Freebase KG and a subset (two domain pairs: movies-music, movie-book) of Amazon Review Data. This new dataset facilitates linking knowledge to bridge within- and cross-domain items for CDR. Then we propose a new framework, KG-aware Neural Collective Matrix Factorization (KG-NeuCMF), leveraging KG to enrich item representations. It first learns item embeddings by graph convolutional autoencoder to capture both domain-specific and domain-general knowledge from adjacent and higher-order neighbours in the KG. Then, we maximize the mutual information between item embeddings learned from the KG and user-item matrix to establish cross-domain relationships for better CDR. Finally, we conduct extensive experiments on the newly constructed dataset and demonstrate that our model significantly outperforms the best-performing baselines.

cs.IR↗

arXiv2022

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal as better alternatives arise. This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims. To make following best model evaluation practices easier, we introduce GEMv2. The new version of the Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers to benefit from each others work. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.

cs.CL↗

arXiv2022

Intra Encoding Complexity Control with a Time-Cost Model for Versatile Video Coding

For the latest video coding standard Versatile Video Coding (VVC), the encoding complexity is much higher than previous video coding standards to achieve a better coding efficiency, especially for intra coding. The complexity becomes a major barrier of its deployment and use. Even with many fast encoding algorithms, it is still practically important to control the encoding complexity to a given level. Inspired by rate control algorithms, we propose a scheme to precisely control the intra encoding complexity of VVC. In the proposed scheme, a Time-PlanarCost (viz. Time-Cost, or T-C) model is utilized for CTU encoding time estimation. By combining a set of predefined parameters and the T-C model, CTU-level complexity can be roughly controlled. Then to achieve a precise picture-level complexity control, a framework is constructed including uneven complexity pre-allocation, preset selection and feedback. Experimental results show that, for the challenging intra coding scenario, the complexity error quickly converges to under 3.21%, while keeping a reasonable time saving and rate-distortion (RD) performance. This proves the efficiency of the proposed methods.

eess.IV↗

arXiv2022

Accelerating Score-based Generative Models for High-Resolution Image Synthesis

Score-based generative models (SGMs) have recently emerged as a promising class of generative models. The key idea is to produce high-quality images by recurrently adding Gaussian noises and gradients to a Gaussian sample until converging to the target distribution, a.k.a. the diffusion sampling. To ensure stability of convergence in sampling and generation quality, however, this sequential sampling process has to take a small step size and many sampling iterations (e.g., 2000). Several acceleration methods have been proposed with focus on low-resolution generation. In this work, we consider the acceleration of high-resolution generation with SGMs, a more challenging yet more important problem. We prove theoretically that this slow convergence drawback is primarily due to the ignorance of the target distribution. Further, we introduce a novel Target Distribution Aware Sampling (TDAS) method by leveraging the structural priors in space and frequency domains. Extensive experiments on CIFAR-10, CelebA, LSUN, and FFHQ datasets validate that TDAS can consistently accelerate state-of-the-art SGMs, particularly on more challenging high resolution (1024x1024) image generation tasks by up to 18.4x, whilst largely maintaining the synthesis quality. With fewer sampling iterations, TDAS can still generate good quality images. In contrast, the existing methods degrade drastically or even fails completely

cs.CV↗

arXiv2022

Direct observation of moiré flat-band breakdown at the edge of magic-angle twisted bilayer graphene

Low-energy moiré flat bands in magic-angle twisted bilayer graphene (tBG) have demonstrated incredible potentials to exhibit rich exotic quantum phenomena. Theoretically, the moiré flat bands of tBG are based on the extended structures, i.e., the moiré patterns with periodic boundary conditions. However, a fundamental question of whether the flat bands can exist in the graphene moiré patterns with a reduced structure symmetry, such as sample edges, remains unanswered. Here, via scanning tunneling microscopy and spectroscopy, we study the local electronic properties of a magic-angle tBG near the sample terminated edge and report a direct observation of breakdown of the moiré flat bands. We show that the moiré electronic structures, including the low-energy flat bands, can sufficiently exist in a complete moiré spot, i.e., a moiré supercell, right at the edge even the translational symmetry of the moiré patterns is broken in one direction. However, the flat-band characteristic is obviously absent in the incomplete moiré spots that are partly terminated by the edge. Our results indicate that a whole moiré spot is sufficient and indispensable for the generation of the effective moiré flat bands in tBG.

cond-mat.mes-hall↗

arXiv2022

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects, especially under a few-shot condition. The current state-of-the-art (SOTA) method, Deep Metric Learning Network (DMLNet), relies on pixel-level metric learning, with which the identification of similar regions having different semantics is difficult. Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning. RAML improves the integrity of the segmented anomaly regions. Moreover, we propose a novel meta-channel aggregation (MCA) module to further separate anomaly regions, forming high-quality sub-region candidates and thereby improving the model performance for OOD objects. To evaluate the proposed RAML, we have conducted extensive experiments and ablation studies on Lost And Found and Road Anomaly datasets for anomaly segmentation and the CityScapes dataset for incremental few-shot learning. The results show that the proposed RAML achieves SOTA performance in both stages of open world segmentation. Our code and appendix are available at https://github.com/czifan/RAML.

cs.CV↗

arXiv2022

Reasoning about Procedures with Natural Language Processing: A Tutorial

This tutorial provides a comprehensive and in-depth view of the research on procedures, primarily in Natural Language Processing. A procedure is a sequence of steps intended to achieve some goal. Understanding procedures in natural language has a long history, with recent breakthroughs made possible by advances in technology. First, we discuss established approaches to collect procedures, by human annotation or extraction from web resources. Then, we examine different angles from which procedures can be reasoned about, as well as ways to represent them. Finally, we enumerate scenarios where procedural knowledge can be applied to the real world.

cs.CL↗