arXiv subjects

Lei Zhao

Publications and source records attributed to Lei Zhao.

At least 145 records · Page 8Linked to original sources

arXiv2023

Randomized Coordinate Subgradient Method for Nonsmooth Composite Optimization

Coordinate-type subgradient methods for addressing nonsmooth optimization problems are relatively underexplored due to the set-valued nature of the subdifferential. In this work, our study focuses on nonsmooth composite optimization problems, encompassing a wide class of convex and weakly convex (nonconvex nonsmooth) problems. By utilizing the chain rule of the composite structure properly, we introduce the Randomized Coordinate Subgradient method (RCS) for tackling this problem class. To the best of our knowledge, this is the first coordinate subgradient method for solving general nonsmooth composite optimization problems. In theory, we consider the linearly bounded subgradients assumption for the objective function, which is more general than the traditional Lipschitz continuity assumption, to account for practical scenarios. We then conduct convergence analysis for RCS in both convex and weakly convex cases based on this generalized Lipschitz-type assumption. Specifically, we establish the $\widetilde{\mathcal{O}}$$(1/\sqrt{k})$ convergence rate in expectation and the $\tilde o(1/\sqrt{k})$ almost sure asymptotic convergence rate in terms of the suboptimality gap when $f$ is convex. For the case when $f$ is weakly convex and its subdifferential satisfies the global metric subregularity property, we derive the $\mathcal{O}(\varepsilon^{-4})$ iteration complexity in expectation. We also establish an asymptotic convergence result. To justify the global metric subregularity property utilized in the analysis, we establish this error bound condition for the concrete (real-valued) robust phase retrieval problem. We also provide a convergence lemma and the relationship between the global metric subregularity properties of a weakly convex function and its Moreau envelope. Finally, we conduct several experiments to demonstrate the possible superiority of RCS over the subgradient method.

math.OC↗

arXiv2023

Classification Committee for Active Deep Object Detection

In object detection, the cost of labeling is much high because it needs not only to confirm the categories of multiple objects in an image but also to accurately determine the bounding boxes of each object. Thus, integrating active learning into object detection will raise pretty positive significance. In this paper, we propose a classification committee for active deep object detection method by introducing a discrepancy mechanism of multiple classifiers for samples' selection when training object detectors. The model contains a main detector and a classification committee. The main detector denotes the target object detector trained from a labeled pool composed of the selected informative images. The role of the classification committee is to select the most informative images according to their uncertainty values from the view of classification, which is expected to focus more on the discrepancy and representative of instances. Specifically, they compute the uncertainty for a specified instance within the image by measuring its discrepancy output by the committee pre-trained via the proposed Maximum Classifiers Discrepancy Group Loss (MCDGL). The most informative images are finally determined by selecting the ones with many high-uncertainty instances. Besides, to mitigate the impact of interference instances, we design a Focus on Positive Instances Loss (FPIL) to make the committee the ability to automatically focus on the representative instances as well as precisely encode their discrepancies for the same instance. Experiments are conducted on Pascal VOC and COCO datasets versus some popular object detectors. And results show that our method outperforms the state-of-the-art active learning methods, which verifies the effectiveness of the proposed method.

cs.CV↗

arXiv2023

StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models

Content and style (C-S) disentanglement is a fundamental problem and critical challenge of style transfer. Existing approaches based on explicit definitions (e.g., Gram matrix) or implicit learning (e.g., GANs) are neither interpretable nor easy to control, resulting in entangled representations and less satisfying results. In this paper, we propose a new C-S disentangled framework for style transfer without using previous assumptions. The key insight is to explicitly extract the content information and implicitly learn the complementary style information, yielding interpretable and controllable C-S disentanglement and style transfer. A simple yet effective CLIP-based style disentanglement loss coordinated with a style reconstruction prior is introduced to disentangle C-S in the CLIP image space. By further leveraging the powerful style removal and generative ability of diffusion models, our framework achieves superior results than state of the art and flexible C-S disentanglement and trade-off control. Our work provides new insights into the C-S disentanglement in style transfer and demonstrates the potential of diffusion models for learning well-disentangled C-S characteristics.

cs.CV↗

arXiv2023

VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs

Neural Radiance Fields (NeRF) has shown great success in novel view synthesis due to its state-of-the-art quality and flexibility. However, NeRF requires dense input views (tens to hundreds) and a long training time (hours to days) for a single scene to generate high-fidelity images. Although using the voxel grids to represent the radiance field can significantly accelerate the optimization process, we observe that for sparse inputs, the voxel grids are more prone to overfitting to the training views and will have holes and floaters, which leads to artifacts. In this paper, we propose VGOS, an approach for fast (3-5 minutes) radiance field reconstruction from sparse inputs (3-10 views) to address these issues. To improve the performance of voxel-based radiance field in sparse input scenarios, we propose two methods: (a) We introduce an incremental voxel training strategy, which prevents overfitting by suppressing the optimization of peripheral voxels in the early stage of reconstruction. (b) We use several regularization techniques to smooth the voxels, which avoids degenerate solutions. Experiments demonstrate that VGOS achieves state-of-the-art performance for sparse inputs with super-fast convergence. Code will be available at https://github.com/SJoJoK/VGOS.

cs.CV↗

arXiv2023

An Augmented Lagrangian Approach to Conically Constrained Non-monotone Variational Inequality Problems

In this paper we consider a non-monotone (mixed) variational inequality model with (nonlinear) convex conic constraints. Through developing an equivalent Lagrangian function-like primal-dual saddle-point system for the VI model in question, we introduce an augmented Lagrangian primal-dual method, to be called ALAVI in the current paper, for solving a general constrained VI model. Under an assumption, to be called the primal-dual variational coherence condition in the paper, we prove the convergence of ALAVI. Next, we show that many existing generalized monotonicity properties are sufficient -- though by no means necessary -- to imply the above mentioned coherence condition, thus are sufficient to ensure convergence of ALAVI. Under that assumption, we further show that ALAVI has in fact an $o(1/\sqrt{k})$ global rate of convergence where $k$ is the iteration count. By introducing a new gap function, this rate further improves to be $O(1/k)$ if the mapping is monotone. Finally, we show that under a metric subregularity condition, even if the VI model may be non-monotone the local convergence rate of ALAVI improves to be linear. Numerical experiments on some randomly generated highly nonlinear and non-monotone VI problems show practical efficacy of the newly proposed method.

math.OC↗

arXiv2023

Ensemble Modeling with Contrastive Knowledge Distillation for Sequential Recommendation

Sequential recommendation aims to capture users' dynamic interest and predicts the next item of users' preference. Most sequential recommendation methods use a deep neural network as sequence encoder to generate user and item representations. Existing works mainly center upon designing a stronger sequence encoder. However, few attempts have been made with training an ensemble of networks as sequence encoders, which is more powerful than a single network because an ensemble of parallel networks can yield diverse prediction results and hence better accuracy. In this paper, we present Ensemble Modeling with contrastive Knowledge Distillation for sequential recommendation (EMKD). Our framework adopts multiple parallel networks as an ensemble of sequence encoders and recommends items based on the output distributions of all these networks. To facilitate knowledge transfer between parallel networks, we propose a novel contrastive knowledge distillation approach, which performs knowledge transfer from the representation level via Intra-network Contrastive Learning (ICL) and Cross-network Contrastive Learning (CCL), as well as Knowledge Distillation (KD) from the logits level via minimizing the Kullback-Leibler divergence between the output distributions of the teacher network and the student network. To leverage contextual information, we train the primary masked item prediction task alongside the auxiliary attribute prediction task as a multi-task learning scheme. Extensive experiments on public benchmark datasets show that EMKD achieves a significant improvement compared with the state-of-the-art methods. Besides, we demonstrate that our ensemble method is a generalized approach that can also improve the performance of other sequential recommenders. Our code is available at this link: https://github.com/hw-du/EMKD.

cs.IR↗

arXiv2023

Sequential Recommendation with Probabilistic Logical Reasoning

Deep learning and symbolic learning are two frequently employed methods in Sequential Recommendation (SR). Recent neural-symbolic SR models demonstrate their potential to enable SR to be equipped with concurrent perception and cognition capacities. However, neural-symbolic SR remains a challenging problem due to open issues like representing users and items in logical reasoning. In this paper, we combine the Deep Neural Network (DNN) SR models with logical reasoning and propose a general framework named Sequential Recommendation with Probabilistic Logical Reasoning (short for SR-PLR). This framework allows SR-PLR to benefit from both similarity matching and logical reasoning by disentangling feature embedding and logic embedding in the DNN and probabilistic logic network. To better capture the uncertainty and evolution of user tastes, SR-PLR embeds users and items with a probabilistic method and conducts probabilistic logical reasoning on users' interaction patterns. Then the feature and logic representations learned from the DNN and logic network are concatenated to make the prediction. Finally, experiments on various sequential recommendation models demonstrate the effectiveness of the SR-PLR.

cs.AI↗

arXiv2023

Real-time Manipulation of Liquid Droplets using Photo-responsive Surfactant

Fast and programmable transport of liquid droplets on a solid substrate is desirable in microfluidic, thermal, biomedical, and energy devices. Past research has focused on designing substrates with asymmetric structures or gradient wettability where droplet behaviors are passively controlled, or by applying external electric, thermal, magnetic, or acoustic stimuli that either require the fabrication of electrodes or a strong applied field. In this work, we demonstrate tunable and programmable droplet motion on liquid-infused surfaces (LIS) and inside solid-surface capillary channels using low-intensity light and photo-responsive surfactants. When illuminated by the light of appropriate wavelengths, the surfactants can reversibly change their molecular conformation thereby tuning interfacial tensions in a multi-phase fluid system. This generates a Marangoni flow that drives droplet motions. With two novel surfactants that we synthesized, we demonstrate fast linear and complex 2D movements of droplets on liquid surfaces, on LIS, and inside microchannels. We also visualized the internal flow pattern using tracer particles and developed simple scaling arguments to explain droplet-size-dependent velocity. The method demonstrated in this study serves as a simple and exciting new approach for the dynamic manipulation of droplets for microfluidic, thermal, and water harvesting devices.

physics.flu-dyn↗

arXiv2023

DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning

Temporal knowledge graphs (TKGs) model the temporal evolution of events and have recently attracted increasing attention. Since TKGs are intrinsically incomplete, it is necessary to reason out missing elements. Although existing TKG reasoning methods have the ability to predict missing future events, they fail to generate explicit reasoning paths and lack explainability. As reinforcement learning (RL) for multi-hop reasoning on traditional knowledge graphs starts showing superior explainability and performance in recent advances, it has opened up opportunities for exploring RL techniques on TKG reasoning. However, the performance of RL-based TKG reasoning methods is limited due to: (1) lack of ability to capture temporal evolution and semantic dependence jointly; (2) excessive reliance on manually designed rewards. To overcome these challenges, we propose an adaptive reinforcement learning model based on attention mechanism (DREAM) to predict missing elements in the future. Specifically, the model contains two components: (1) a multi-faceted attention representation learning method that captures semantic dependence and temporal evolution jointly; (2) an adaptive RL framework that conducts multi-hop reasoning by adaptively learning the reward functions. Experimental results demonstrate DREAM outperforms state-of-the-art models on public dataset

cs.AI↗

arXiv2023

Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning

This paper presents a new adversarial training framework for image inpainting with segmentation confusion adversarial training (SCAT) and contrastive learning. SCAT plays an adversarial game between an inpainting generator and a segmentation network, which provides pixel-level local training signals and can adapt to images with free-form holes. By combining SCAT with standard global adversarial training, the new adversarial training framework exhibits the following three advantages simultaneously: (1) the global consistency of the repaired image, (2) the local fine texture details of the repaired image, and (3) the flexibility of handling images with free-form holes. Moreover, we propose the textural and semantic contrastive learning losses to stabilize and improve our inpainting model's training by exploiting the feature representation space of the discriminator, in which the inpainting images are pulled closer to the ground truth images but pushed farther from the corrupted images. The proposed contrastive losses better guide the repaired images to move from the corrupted image data points to the real image data points in the feature representation space, resulting in more realistic completed images. We conduct extensive experiments on two benchmark datasets, demonstrating our model's effectiveness and superiority both qualitatively and quantitatively.

cs.CV↗

arXiv2023

Integrable Mechanical Billiards in Higher Dimensional Space Forms

In this article, we consider mechanical billiard systems defined with Lagrange's integrable extension of Euler's two-center problems in the Euclidean space, on the sphere, and in the hyperbolic space of arbitrary dimension $n \ge 3$. In the three-dimensional Euclidean space, we show that the billiard systems with any finite combination of quadrics having two foci at the Kepler centers are integrable. The same holds for the projections of these systems on the three-dimensional sphere and the hyperbolic space by means of central projection. With the same approach, we also extend these results to the $n$-dimensional cases.

math.DS↗

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↗