arXiv subjects

Lei Zhao

Publications and source records attributed to Lei Zhao.

At least 163 records · Page 9Linked to original sources

arXiv2023

OppLoD: the Opponency based Looming Detector, Model Extension of Looming Sensitivity from LGMD to LPLC2

Looming detection plays an important role in insect collision prevention systems. As a vital capability evolutionary survival, it has been extensively studied in neuroscience and is attracting increasing research interest in robotics due to its close relationship with collision detection and navigation. Visual cues such as angular size, angular velocity, and expansion have been widely studied for looming detection by means of optic flow or elementary neural computing research. However, a critical visual motion cue has been long neglected because it is so easy to be confused with expansion, that is radial-opponent-motion (ROM). Recent research on the discovery of LPLC2, a ROM-sensitive neuron in Drosophila, has revealed its ultra-selectivity because it only responds to stimuli with focal, outward movement. This characteristic of ROM-sensitivity is consistent with the demand for collision detection because it is strongly associated with danger looming that is moving towards the center of the observer. Thus, we hope to extend the well-studied neural model of the lobula giant movement detector (LGMD) with ROM-sensibility in order to enhance robustness and accuracy at the same time. In this paper, we investigate the potential to extend an image velocity-based looming detector, the lobula giant movement detector (LGMD), with ROM-sensibility. To achieve this, we propose the mathematical definition of ROM and its main property, the radial motion opponency (RMO). Then, a synaptic neuropile that analogizes the synaptic processing of LPLC2 is proposed in the form of lateral inhibition and attention. Thus, our proposed model is the first to perform both image velocity selectivity and ROM sensitivity. Systematic experiments are conducted to exhibit the huge potential of the proposed bio-inspired looming detector.

cs.CV↗

arXiv2022

Long-Document Cross-Lingual Summarization

Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language. CLS has attracted wide research attention due to its practical significance in the multi-lingual world. Though great contributions have been made, existing CLS works typically focus on short documents, such as news articles, short dialogues and guides. Different from these short texts, long documents such as academic articles and business reports usually discuss complicated subjects and consist of thousands of words, making them non-trivial to process and summarize. To promote CLS research on long documents, we construct Perseus, the first long-document CLS dataset which collects about 94K Chinese scientific documents paired with English summaries. The average length of documents in Perseus is more than two thousand tokens. As a preliminary study on long-document CLS, we build and evaluate various CLS baselines, including pipeline and end-to-end methods. Experimental results on Perseus show the superiority of the end-to-end baseline, outperforming the strong pipeline models equipped with sophisticated machine translation systems. Furthermore, to provide a deeper understanding, we manually analyze the model outputs and discuss specific challenges faced by current approaches. We hope that our work could benchmark long-document CLS and benefit future studies.

cs.CL↗

arXiv2022

MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer

Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources, which heavily hinders their further applications. In this paper, we tackle this dilemma by learning a straightforward and lightweight model, dubbed MicroAST. The key insight is to completely abandon the use of cumbersome pre-trained Deep Convolutional Neural Networks (e.g., VGG) at inference. Instead, we design two micro encoders (content and style encoders) and one micro decoder for style transfer. The content encoder aims at extracting the main structure of the content image. The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations. In addition, to boost the ability of the style encoder to extract more distinct and representative style signals, we also introduce a new style signal contrastive loss in our model. Compared to the state of the art, our MicroAST not only produces visually superior results but also is 5-73 times smaller and 6-18 times faster, for the first time enabling super-fast (about 0.5 seconds) AST at 4K ultra-resolutions. Code is available at https://github.com/EndyWon/MicroAST.

cs.CV↗

arXiv2022

Estimation of Solar Observations with the Five-hundred-meter Aperture Spherical Radio Telescope (FAST)

We present the estimation of the solar observation with the Five-hundred-meter Aperture Spherical radio Telescope (FAST). For both the quite Sun and the Sun with radio bursts, when pointing directly to the Sun, the total power received by FAST would be out of the safe operational range of the signal chain, even resulting in the damage to the receiver. As a conclusion, the Sun should be kept at least $\sim 2^{\circ}$ away from the main beam during the observing at $\sim 1.25 {\ \rm GHz}$. The separation for lower frequency should be larger. For simplicity, the angular separation between the FAST beam and the Sun is suggested to be $\sim 5^{\circ}$ for observations on 200 MHz or higher bands.

astro-ph.IM↗

arXiv2022

Study of Hybrid MicroPattern Gas Detector with CsI Photocathode For Super Tau-Charm Factory RICH

Super tau-Charm facility(STCF) is a future electron-position collider operating at tau-Charm energy region aimed to study hadron structure and spectroscopy. The baseline design of the STCF barrel particle identification(PID) detector in the momentum range up to 2 GeV/c is provided by a Ring Imaging Cherenkov Counter(RICH). The architecture of the RICH is an approximately focusing design with liquid perfluorohexane sealed in the quartz container as radiator and a hybrid combination of a CsI coated layers of THGEMs and a Micromegas as the photo-electron detector. A 16*16 cm^2 prototype with quartz radiator has been built and tested at DESY. It was stably operated with 10^5 effective gain. In this paper, the design, the performance, the reconstruction algorithm and the systematic error for single photon electron angular resolution in the aspect of RICH detectors are discusses.

physics.ins-det↗

arXiv2022

An Investigation into Whitening Loss for Self-supervised Learning

A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of positive pairs under the conditioning that the embeddings from different views are whitened. In this paper, we propose a framework with an informative indicator to analyze whitening loss, which provides a clue to demystify several interesting phenomena as well as a pivoting point connecting to other SSL methods. We reveal that batch whitening (BW) based methods do not impose whitening constraints on the embedding, but they only require the embedding to be full-rank. This full-rank constraint is also sufficient to avoid dimensional collapse. Based on our analysis, we propose channel whitening with random group partition (CW-RGP), which exploits the advantages of BW-based methods in preventing collapse and avoids their disadvantages requiring large batch size. Experimental results on ImageNet classification and COCO object detection reveal that the proposed CW-RGP possesses a promising potential for learning good representations. The code is available at https://github.com/winci-ai/CW-RGP.

cs.CV↗

arXiv2022

Does Attention Mechanism Possess the Feature of Human Reading? A Perspective of Sentiment Classification Task

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize the attention mechanism in deep learning models. But these studies lack to explain the rationality of this approach. Whether the attention mechanism possesses this feature of human reading needs to be explored. [Design/methodology/approach] We conducted experiments on a sentiment classification task. Firstly, we obtained eye-tracking values from two open-source eye-tracking corpora to describe the feature of human reading. Then, the machine attention values of each sentence were learned from a sentiment classification model. Finally, a comparison was conducted to analyze machine attention values and eye-tracking values. [Findings] Through experiments, we found the attention mechanism can focus on important words, such as adjectives, adverbs, and sentiment words, which are valuable for judging the sentiment of sentences on the sentiment classification task. It possesses the feature of human reading, focusing on important words in sentences when reading. Due to the insufficient learning of the attention mechanism, some words are wrongly focused. The eye-tracking values can help the attention mechanism correct this error and improve the model performance. [Originality/value] Our research not only provides a reasonable explanation for the study of using eye-tracking values to optimize the attention mechanism, but also provides new inspiration for the interpretability of attention mechanism.

cs.CL↗

arXiv2022

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

Inductive link prediction (ILP) is to predict links for unseen entities in emerging knowledge graphs (KGs), considering the evolving nature of KGs. A more challenging scenario is that emerging KGs consist of only unseen entities, called as disconnected emerging KGs (DEKGs). Existing studies for DEKGs only focus on predicting enclosing links, i.e., predicting links inside the emerging KG. The bridging links, which carry the evolutionary information from the original KG to DEKG, have not been investigated by previous work so far. To fill in the gap, we propose a novel model entitled DEKG-ILP (Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction) that consists of the following two components. (1) The module CLRM (Contrastive Learning-based Relation-specific Feature Modeling) is developed to extract global relation-based semantic features that are shared between original KGs and DEKGs with a novel sampling strategy. (2) The module GSM (GNN-based Subgraph Modeling) is proposed to extract the local subgraph topological information around each link in KGs. The extensive experiments conducted on several benchmark datasets demonstrate that DEKG-ILP has obvious performance improvements compared with state-of-the-art methods for both enclosing and bridging link prediction. The source code is available online.

cs.LG↗

arXiv2022

MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning

Multi-modal knowledge graphs (MKGs) include not only the relation triplets, but also related multi-modal auxiliary data (i.e., texts and images), which enhance the diversity of knowledge. However, the natural incompleteness has significantly hindered the applications of MKGs. To tackle the problem, existing studies employ the embedding-based reasoning models to infer the missing knowledge after fusing the multi-modal features. However, the reasoning performance of these methods is limited due to the following problems: (1) ineffective fusion of multi-modal auxiliary features; (2) lack of complex reasoning ability as well as inability to conduct the multi-hop reasoning which is able to infer more missing knowledge. To overcome these problems, we propose a novel model entitled MMKGR (Multi-hop Multi-modal Knowledge Graph Reasoning). Specifically, the model contains the following two components: (1) a unified gate-attention network which is designed to generate effective multi-modal complementary features through sufficient attention interaction and noise reduction; (2) a complementary feature-aware reinforcement learning method which is proposed to predict missing elements by performing the multi-hop reasoning process, based on the features obtained in component (1). The experimental results demonstrate that MMKGR outperforms the state-of-the-art approaches in the MKG reasoning task.

cs.AI↗

arXiv2022

AesUST: Towards Aesthetic-Enhanced Universal Style Transfer

Recent studies have shown remarkable success in universal style transfer which transfers arbitrary visual styles to content images. However, existing approaches suffer from the aesthetic-unrealistic problem that introduces disharmonious patterns and evident artifacts, making the results easy to spot from real paintings. To address this limitation, we propose AesUST, a novel Aesthetic-enhanced Universal Style Transfer approach that can generate aesthetically more realistic and pleasing results for arbitrary styles. Specifically, our approach introduces an aesthetic discriminator to learn the universal human-delightful aesthetic features from a large corpus of artist-created paintings. Then, the aesthetic features are incorporated to enhance the style transfer process via a novel Aesthetic-aware Style-Attention (AesSA) module. Such an AesSA module enables our AesUST to efficiently and flexibly integrate the style patterns according to the global aesthetic channel distribution of the style image and the local semantic spatial distribution of the content image. Moreover, we also develop a new two-stage transfer training strategy with two aesthetic regularizations to train our model more effectively, further improving stylization performance. Extensive experiments and user studies demonstrate that our approach synthesizes aesthetically more harmonious and realistic results than state of the art, greatly narrowing the disparity with real artist-created paintings. Our code is available at https://github.com/EndyWon/AesUST.

cs.CV↗

arXiv2022

Contrastive Learning with Bidirectional Transformers for Sequential Recommendation

Contrastive learning with Transformer-based sequence encoder has gained predominance for sequential recommendation. It maximizes the agreements between paired sequence augmentations that share similar semantics. However, existing contrastive learning approaches in sequential recommendation mainly center upon left-to-right unidirectional Transformers as base encoders, which are suboptimal for sequential recommendation because user behaviors may not be a rigid left-to-right sequence. To tackle that, we propose a novel framework named \textbf{C}ontrastive learning with \textbf{Bi}directional \textbf{T}ransformers for sequential recommendation (\textbf{CBiT}). Specifically, we first apply the slide window technique for long user sequences in bidirectional Transformers, which allows for a more fine-grained division of user sequences. Then we combine the cloze task mask and the dropout mask to generate high-quality positive samples and perform multi-pair contrastive learning, which demonstrates better performance and adaptability compared with the normal one-pair contrastive learning. Moreover, we introduce a novel dynamic loss reweighting strategy to balance between the cloze task loss and the contrastive loss. Experiment results on three public benchmark datasets show that our model outperforms state-of-the-art models for sequential recommendation.

cs.IR↗

arXiv2022

RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation

Grounding dialogue system with external knowledge is a promising way to improve the quality of responses. Most existing works adopt knowledge graphs (KGs) as the external resources, paying attention to the contribution of entities in the last utterance of the dialogue for context understanding and response generation. Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored. To this end, we propose a Relation Transition aware Knowledge-Grounded Dialogue Generation model (RT-KGD). Specifically, inspired by the latent logic of human conversation, our model integrates dialogue-level relation transition regularities with turn-level entity semantic information. In this manner, the interaction between knowledge is considered to produce abundant clues for predicting the appropriate knowledge and generating coherent responses. The experimental results on both automatic evaluation and manual evaluation indicate that our model outperforms state-of-the-art baselines.

cs.CL↗

arXiv2022

A numerical analysis of planar central and balanced configurations in the (n+1)-body problem with a small mass

Two numerical algorithms for analyzing planar central and balanced configurations in the $(n+1)$-body problem with a small mass are presented. The first one relies on a direct solution method of the $(n+1)$-body problem by using a stochastic optimization approach, while the second one relies on an analytic-continuation method, which involves the solutions of the $n$-body and the restricted $(n+1)$-body problem, and the application of a local search procedure to compute the final $(n+1)$-body configuration in the neighborhood of the configuration obtained at the first two steps. Some exemplary central and balanced configurations in the cases $n=4,5,6$ are shown.

math.DS↗

arXiv2022

Unified chemical theory of structure and bonding in elemental metals

Most elemental metals under ambient conditions adopt simple structures such as BCC, FCC and HCP in specific groupings across the Periodic Table, and on compression, many of these elements undergo transitions to surprisingly complex structures, including open and low-symmetry phases not expected from conventional free-electron based theories of metals. First-principles calculations have been able to reproduce many observed structures and transitions, but a unified, predictive theory of bonding that underlies this behavior is not yet in hand. We propose a remarkably simple theory based on large-scale high-throughput calculations of the elements over a broad range of thermodynamic conditions. The results broaden the conventional concept of metallic bonding with a new perspective that both explains the stability of different simple structures as well as lower symmetry phases arising from electron localization at interstitial sites in these structures. The success of this simple framework reveals the important role of chemical interactions in governing the structures and electronic properties of simple metals.

cond-mat.mtrl-sci↗

arXiv2022

Evolutionary Mutation-based Fuzzing as Monte Carlo Tree Search

Coverage-based greybox fuzzing (CGF) has been approved to be effective in finding security vulnerabilities. Seed scheduling, the process of selecting an input as the seed from the seed pool for the next fuzzing iteration, plays a central role in CGF. Although numerous seed scheduling strategies have been proposed, most of them treat these seeds independently and do not explicitly consider the relationships among the seeds. In this study, we make a key observation that the relationships among seeds are valuable for seed scheduling. We design and propose a "seed mutation tree" by investigating and leveraging the mutation relationships among seeds. With the "seed mutation tree", we further model the seed scheduling problem as a Monte-Carlo Tree Search (MCTS) problem. That is, we select the next seed for fuzzing by walking this "seed mutation tree" through an optimal path, based on the estimation of MCTS. We implement two prototypes, AlphaFuzz on top of AFL and AlphaFuzz++ on top of AFL++. The evaluation results on three datasets (the UniFuzz dataset, the CGC binaries, and 12 real-world binaries) show that AlphaFuzz and AlphaFuzz++ outperform state-of-the-art fuzzers with higher code coverage and more discovered vulnerabilities. In particular, AlphaFuzz discovers 3 new vulnerabilities with CVEs.

cs.SE↗

arXiv2022

DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer

Gram-based and patch-based approaches are two important research lines of style transfer. Recent diversified Gram-based methods have been able to produce multiple and diverse stylized outputs for the same content and style images. However, as another widespread research interest, the diversity of patch-based methods remains challenging due to the stereotyped style swapping process based on nearest patch matching. To resolve this dilemma, in this paper, we dive into the crux of existing patch-based methods and propose a universal and efficient module, termed DivSwapper, for diversified patch-based arbitrary style transfer. The key insight is to use an essential intuition that neural patches with higher activation values could contribute more to diversity. Our DivSwapper is plug-and-play and can be easily integrated into existing patch-based and Gram-based methods to generate diverse results for arbitrary styles. We conduct theoretical analyses and extensive experiments to demonstrate the effectiveness of our method, and compared with state-of-the-art algorithms, it shows superiority in diversity, quality, and efficiency.

cs.CV↗

arXiv2022

Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation

Sequential Recommendation aims to predict the next item based on user behaviour. Recently, Self-Supervised Learning (SSL) has been proposed to improve recommendation performance. However, most of existing SSL methods use a uniform data augmentation scheme, which loses the sequence correlation of an original sequence. To this end, in this paper, we propose a Learnable Model Augmentation self-supervised learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes model augmentation as a supplementary method for data augmentation to generate views. Then, LMA4Rec uses learnable Bernoulli dropout to implement model augmentation learnable operations. Next, self-supervised learning is used between the contrastive views to extract self-supervised signals from an original sequence. Finally, experiments on three public datasets show that the LMA4Rec method effectively improves sequential recommendation performance compared with baseline methods.

cs.IR↗

arXiv2022

Projective Integrable Mechanical Billiards

In this paper, we use the projective dynamical approach to integrable mechanical billiards as in [Zhao, 2021] to establish the integrability of natural mechanical billiards with the Lagrange problem, which is the superposition of two Kepler problems and a Hooke problem, with the Hooke center at the middle of the Kepler centers, as the underlying mechanical systems, and with any combinations of confocal conic sections with foci at the Kepler centers as the reflection wall, in the plane, on the sphere, and in the hyperbolic plane. This covers many previously known integrable mechanical billiards, especially the integrable Hooke, Kepler and two-center billiards in the plane, as has been investigated in [Takeuchi-Zhao, 2021], as subcases. The approach of [Takeuchi-Zhao, 2021] based on conformal correspondence has been also applied to integrable Kepler billiards in the hyperbolic plane to illustrate their equivalence with the corresponding integrable Hooke billiards on the hemisphere and in the hyperbolic plane as well.

math.DS↗