Searcharxiv⌕ Search

arXiv subjects

Lei Zhou

Publications and source records attributed to Lei Zhou.

At least 91 records · Page 5Linked to original sources
arXiv2023

Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation

Temporal knowledge graphs, representing the dynamic relationships and interactions between entities over time, have been identified as a promising approach for event forecasting. However, a limitation of most temporal knowledge graph reasoning methods is their heavy reliance on the recurrence or periodicity of events, which brings challenges to inferring future events related to entities that lack historical interaction. In fact, the current state of affairs is often the result of a combination of historical information and underlying factors that are not directly observable. To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities that best match the given query. Simultaneously, by launching contrastive learning, it trains representations of queries to probe whether the current moment is more dependent on historical or non-historical events. These representations further help train a binary classifier, whose output is a boolean mask, indicating the related entities in the search space. During the inference process, CENET employs a mask-based strategy to generate the final results. We evaluate our proposed model on five benchmark graphs. The results demonstrate that CENET significantly outperforms all existing methods in most metrics, achieving at least 8.3% relative improvement of Hits@1 over previous state-of-the-art baselines on event-based datasets.

cs.AI↗
arXiv2023

PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex Scenes

Vision-based grasp estimation is an essential part of robotic manipulation tasks in the real world. Existing planar grasp estimation algorithms have been demonstrated to work well in relatively simple scenes. But when it comes to complex scenes, such as cluttered scenes with messy backgrounds and moving objects, the algorithms from previous works are prone to generate inaccurate and unstable grasping contact points. In this work, we first study the existing planar grasp estimation algorithms and analyze the related challenges in complex scenes. Secondly, we design a Pixel-wise Efficient Grasp Generation Network (PEGG-Net) to tackle the problem of grasping in complex scenes. PEGG-Net can achieve improved state-of-the-art performance on the Cornell dataset (98.9%) and second-best performance on the Jacquard dataset (93.8%), outperforming other existing algorithms without the introduction of complex structures. Thirdly, PEGG-Net could operate in a closed-loop manner for added robustness in dynamic environments using position-based visual servoing (PBVS). Finally, we conduct real-world experiments on static, dynamic, and cluttered objects in different complex scenes. The results show that our proposed network achieves a high success rate in grasping irregular objects, household objects, and workshop tools. To benefit the community, our trained model and supplementary materials are available at https://github.com/HZWang96/PEGG-Net.

cs.CV↗
arXiv2023

Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of "Zero-Shot Open-Set Recognition" (ZS-OSR), where a model is trained under the ZSL setting but it is required to accurately classify samples from the unseen classes while being able to reject samples from the unknown classes during inference. We perform large experiments on combining existing state-of-the-art ZSL and OSR models for the ZS-OSR task on four widely used datasets adapted from the ZSL task, and reveal that ZS-OSR is a non-trivial task as the simply combined solutions perform badly in distinguishing the unseen-class and unknown-class samples. We further introduce a novel approach specifically designed for ZS-OSR, in which our model learns to generate adversarial semantic embeddings of the unknown classes to train an unknowns-informed ZS-OSR classifier. Extensive empirical results show that our method 1) substantially outperforms the combined solutions in detecting the unknown classes while retaining the classification accuracy on the unseen classes and 2) achieves similar superiority under generalized ZS-OSR settings.

cs.CV↗
arXiv2023

Learning swimming via deep reinforcement learning

For decades, people have been seeking for fishlike flapping motions that can realize underwater propulsion with low energy cost. Complexity of the nonstationary flow field around the flapping body makes this problem very difficult. In earlier studies, motion patterns are usually prescribed as certain periodic functions which constrains the following optimization process in a small subdomain of the whole motion space. In this work, to avoid this motion constraint, a variational autoencoder (VAE) is designed to compress various flapping motions into a simple action vector. Then we let a flapping airfoil continuously interact with water tunnel environment and adjust its action accordingly through a reinforcement learning (RL) framework. By this automatic close-looped experiment, we obtain several motion patterns that can result in high hydrodynamic efficiency comparing to pure harmonic motions with the same thrust level. And we find that, after numerous trials and errors, RL trainings in current experiment always converge to motion patterns that are close to harmonic motions. In other words, current work proves that harmonic motion with appropriate amplitude and frequency is always an optimal choice for efficient underwater propulsion. Furthermore, the RL framework proposed here can be also extended to the study of other complex swimming problems, which might pave the way for the creation of a robotic fish that can swim like a real fish.

cs.RO↗
arXiv2023

Revisiting Network Value: Sublinear Knowledge Law

Three influential laws, namely Sarnoff's Law, Metcalfe's Law, and Reed's Law, have been established to describe network value in terms of the number of neighbors, edges, and subgraphs. Here, we highlight the coexistence of these laws in citation networks for the first time, utilizing the Deep-time Digital Earth academic literature. We further introduce a novel concept called the sublinear knowledge law, which demonstrates that knowledge growth is notably slower than both the growth rate of network size and the rates outlined by the aforementioned traditional laws. These results offer an innovative perspective while also filling a gap regarding network value.

physics.soc-ph↗
arXiv2023

Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual information to infer masked image regions. We believe that this context aggregation ability is particularly essential to the medical image domain where each anatomical structure is functionally and mechanically connected to other structures and regions. Because there is no ImageNet-scale medical image dataset for pre-training, we investigate a self pre-training paradigm with MAE for medical image analysis tasks. Our method pre-trains a ViT on the training set of the target data instead of another dataset. Thus, self pre-training can benefit more scenarios where pre-training data is hard to acquire. Our experimental results show that MAE self pre-training markedly improves diverse medical image tasks including chest X-ray disease classification, abdominal CT multi-organ segmentation, and MRI brain tumor segmentation. Code is available at https://github.com/cvlab-stonybrook/SelfMedMAE

eess.IV↗
arXiv2023

Nonrelativistic and nonmagnetic control of terahertz charge currents via electrical anisotropy in RuO2 and IrO2

Precise and ultrafast control over photo-induced charge currents across nanoscale interfaces could lead to important applications in energy harvesting, ultrafast electronics, and coherent terahertz sources. Recent studies have shown that several relativistic mechanisms, including inverse spin-Hall effect, inverse Rashba-Edelstein effect and inverse spin-orbit-torque effect, can convert longitudinally injected spin-polarized currents from magnetic materials to transverse charge currents, thereby harnessing these currents for terahertz generation. However, these mechanisms typically require external magnetic fields and suffer from low spin-polarization rates and low efficiencies of relativistic spin-to-charge conversion. In this work, we present a novel nonrelativistic and nonmagnetic mechanism that directly utilizes the photo-excited high-density charge currents across the interface. We demonstrate that the electrical anisotropy of conductive oxides RuO2 and IrO2 can effectively deflect injected charge currents to the transverse direction, resulting in efficient and broadband terahertz radiation. Importantly, this new mechanism has the potential to offer much higher conversion efficiency compared to previous methods, as conductive materials with large electrical anisotropy are readily available, whereas further increasing the spin-Hall angle of heavy-metal materials would be challenging. Our new findings offer exciting possibilities for directly utilizing these photo-excited high-density currents across metallic interfaces for ultrafast electronics and terahertz spectroscopy.

physics.optics↗
arXiv2023

Token Sparsification for Faster Medical Image Segmentation

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens. To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline. We first empirically show that naively applying existing approaches from classification token pruning and masked image modeling (MIM) leads to failure and inefficient training caused by inappropriate sampling algorithms and the low quality of the restored dense features. In this paper, we propose Soft-topK Token Pruning (STP) and Multi-layer Token Assembly (MTA) to address these problems. In sparse encoding, STP predicts token importance scores with a lightweight sub-network and samples the topK tokens. The intractable topK gradients are approximated through a continuous perturbed score distribution. In token completion, MTA restores a full token sequence by assembling both sparse output tokens and pruned multi-layer intermediate ones. The last dense decoding stage is compatible with existing segmentation decoders, e.g., UNETR. Experiments show SCD pipelines equipped with STP and MTA are much faster than baselines without token pruning in both training (up to 120% higher throughput and inference up to 60.6% higher throughput) while maintaining segmentation quality.

cs.CV↗
arXiv2023

Learning and Matching Multi-View Descriptors for Registration of Point Clouds

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed by the design of discriminative 3D local descriptors on the one hand, and the development of robust matching strategies on the other hand. In this work, we first propose a multi-view local descriptor, which is learned from the images of multiple views, for the description of 3D keypoints. Then, we develop a robust matching approach, aiming at rejecting outlier matches based on the efficient inference via belief propagation on the defined graphical model. We have demonstrated the boost of our approaches to registration on the public scanning and multi-view stereo datasets. The superior performance has been verified by the intensive comparisons against a variety of descriptors and matching methods.

cs.CV↗
arXiv2023

Bokeh Rendering Based on Adaptive Depth Calibration Network

Bokeh rendering is a popular and effective technique used in photography to create an aesthetically pleasing effect. It is widely used to blur the background and highlight the subject in the foreground, thereby drawing the viewer's attention to the main focus of the image. In traditional digital single-lens reflex cameras (DSLRs), this effect is achieved through the use of a large aperture lens. This allows the camera to capture images with shallow depth-of-field, in which only a small area of the image is in sharp focus, while the rest of the image is blurred. However, the hardware embedded in mobile phones is typically much smaller and more limited than that found in DSLRs. Consequently, mobile phones are not able to capture natural shallow depth-of-field photos, which can be a significant limitation for mobile photography. To address this challenge, in this paper, we propose a novel method for bokeh rendering using the Vision Transformer, a recent and powerful deep learning architecture. Our approach employs an adaptive depth calibration network that acts as a confidence level to compensate for errors in monocular depth estimation. This network is used to supervise the rendering process in conjunction with depth information, allowing for the generation of high-quality bokeh images at high resolutions. Our experiments demonstrate that our proposed method outperforms state-of-the-art methods, achieving about 24.7% improvements on LPIPS and obtaining higher PSNR scores.

cs.CV↗
arXiv2023

Sequential Structure and Control Co-design of Lightweight Precision Stages with Active control of flexible modes

Precision motion stages are playing a prominent role in various manufacturing equipment. The drastically increasing demand for higher throughput in integrated circuit (IC) manufacturing and inspection calls for the next-generation precision stages that have light weight and high control bandwidth simultaneously. In today's design techniques, the stage's first flexible mode is limiting its achievable control bandwidth, which enforces a trade-off between the stage's acceleration and closed-loop stiffness and thus limits the system's overall performance. To overcome this challenge, this paper proposes a new hardware design and control framework for lightweight precision motion stages with the stage's low-frequency flexible modes actively controlled. Our method proposes to minimize the resonance frequency of the controlled mode to reduce the stage's weight, and to maximize that of the uncontrolled mode to enable high control bandwidth. In addition, the proposed framework determines the placement of the actuators and sensors to maximize the controllability/observability of the stage's controlled flexible mode while minimizing that of the uncontrolled mode, which effectively simplifies the controller designs. Two case studies are used to evaluate the effectiveness of the proposed framework. Simulation results show that the stage designed using the proposed method has a weight reduction of more than 55% compared to a baseline stage design. Improvement in control bandwidth was also achieved. These results demonstrate the effectiveness of the proposed method in achieving lightweight precision positioning stages with high acceleration, bandwidth, and precision.

eess.SY↗
arXiv2022

Cross-Modal Similarity-Based Curriculum Learning for Image Captioning

Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences in their learning difficulties. Several image captioning approaches introduce curriculum learning methods that present training data with increasing levels of difficulty. However, their difficulty measurements are either based on domain-specific features or prior model training. In this paper, we propose a simple yet efficient difficulty measurement for image captioning using cross-modal similarity calculated by a pretrained vision-language model. Experiments on the COCO and Flickr30k datasets show that our proposed approach achieves superior performance and competitive convergence speed to baselines without requiring heuristics or incurring additional training costs. Moreover, the higher model performance on difficult examples and unseen data also demonstrates the generalization ability.

cs.CV↗
arXiv2022

Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation

Automated polyp segmentation technology plays an important role in diagnosing intestinal diseases, such as tumors and precancerous lesions. Previous works have typically trained convolution-based U-Net or Transformer-based neural network architectures with labeled data. However, the available public polyp segmentation datasets are too small to train the network sufficiently, suppressing each network's potential performance. To alleviate this issue, we propose a universal data augmentation technology to synthesize more data from the existing datasets. Specifically, we paste the polyp area into the same image's background in a spatial-exclusive manner to obtain a combinatorial number of new images. Extensive experiments on various networks and datasets show that the proposed method enhances the data efficiency and achieves consistent improvements over baselines. Finally, we hit a new state of the art in this task. We will release the code soon.

eess.IV↗
arXiv2022

Geometry-dependent skin effects in reciprocal photonic crystals

Skin effect that all eigenmodes within a frequency range become edge states is dictated by the topological properties of complex eigenvalues unique in non-Hermitian systems. The prevailing attempts to realize such a fascinating effect are confined to either one-dimensional or nonreciprocal systems exhibiting asymmetric couplings. Here, inspired by a recent model Hamiltonian theory, we propose a realistic reciprocal two-dimensional (2D) photonic crystal (PhC) system that shows the desired skin effect. Specifically, we establish a routine for designing such non-Hermitian systems via revealing the inherent connections between the non-trivial eigenvalue topology of order-2 exceptional points (EPs) and the skin effects. Guided by the proposed strategy, we successfully design a 2D PhC that possesses the EPs with nonzero eigenvalue winding numbers. The spectral area along a specific wavevector direction is then formed by leveraging the symmetry of the macroscopic geometry and the unit cell. The projected-band-structure calculations are performed to demonstrate that the desired skin effect exists at the specific crystalline interfaces. We finally employ time-domain simulations to vividly illustrate this phenomenon by exciting a pulse at the center of a finite-sized PhC. Our results form a solid basis for further experimental confirmations and applications of the skin effect.

physics.optics↗
arXiv2022

Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning

Precision robotic manipulation tasks (insertion, screwing, precisely pick, precisely place) are required in many scenarios. Previous methods achieved good performance on such manipulation tasks. However, such methods typically require tedious calibration or expensive sensors. 3D/RGB-D cameras and torque/force sensors add to the cost of the robotic application and may not always be economical. In this work, we aim to solve these but using only weak-calibrated and low-cost webcams. We propose Binocular Alignment Learning (BAL), which could automatically learn the eye-hand coordination and points alignment capabilities to solve the four tasks. Our work focuses on working with unknown eye-hand coordination and proposes different ways of performing eye-in-hand camera calibration automatically. The algorithm was trained in simulation and used a practical pipeline to achieve sim2real and test it on the real robot. Our method achieves a competitively good result with minimal cost on the four tasks.

cs.RO↗
arXiv2022

Automatic detection of multilevel communities: scalable and resolution-limit-free

Community structure is one of the most important features of complex networks. Modularity-based methods for community detection typically rely on heuristic algorithms to optimize a specific community quality function. Such methods are limited by two major defects: (1) the resolution limit problem, which prohibits communities of heterogeneous sizes being simultaneously detected, and (2) divergent outputs of the heuristic algorithm, which make it difficult to differentiate relevant and irrelevant results. In this paper, we propose an improved method for community detection based on a scalable community "fitness function." We introduced a new parameter to enhance its scalability, and a strict strategy to filter the outputs. Due to the scalability, on the one hand our method is free of the resolution limit problem and performs excellently on large heterogeneous networks, while on the other hand it is capable of detecting more levels of communities than previous methods in deep hierarchical networks. Moreover, our strict strategy automatically removes redundant and irrelevant results, without any artificial selection. As a result, our method neatly outputs only the stable and unique communities, which are largely interpretable by the a priori knowledge about the network, including the implanted structures within synthetic networks, or metadata for real-world networks.

physics.soc-ph↗
arXiv2022

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. To achieve this goal, first, flow maps are regressed in each cross attention phase to locate the center of search region. Next, a sampling grid is generated around the center, whose size, instead of being empirically configured as fixed, is adaptively computed from a pixel uncertainty estimated along with the flow map. Finally, attention is computed across two images within derived regions, referred to as attention span. By these means, we are able to not only maintain long-range dependencies, but also enable fine-grained attention among pixels of high relevance that compensates essential locality and piece-wise smoothness in matching tasks. State-of-the-art accuracy on a wide range of evaluation benchmarks validates the strong matching capability of our method.

cs.CV↗
arXiv2022

Learning Prototype via Placeholder for Zero-shot Recognition

Zero-shot learning (ZSL) aims to recognize unseen classes by exploiting semantic descriptions shared between seen classes and unseen classes. Current methods show that it is effective to learn visual-semantic alignment by projecting semantic embeddings into the visual space as class prototypes. However, such a projection function is only concerned with seen classes. When applied to unseen classes, the prototypes often perform suboptimally due to domain shift. In this paper, we propose to learn prototypes via placeholders, termed LPL, to eliminate the domain shift between seen and unseen classes. Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space. Placed between seen classes, the placeholders encourage prototypes of seen classes to be highly dispersed. And more space is spared for the insertion of well-separated unseen ones. Empirically, well-separated prototypes help counteract visual-semantic misalignment caused by domain shift. Furthermore, we exploit a novel semantic-oriented fine-tuning to guarantee the semantic reliability of placeholders. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of LPL over the state-of-the-art methods. Code is available at https://github.com/zaiquanyang/LPL.

cs.CV↗