arXiv subjects

Kai Zhao

Publications and source records attributed to Kai Zhao.

At least 181 records · Page 10Linked to original sources

arXiv2022

Learning an Efficient Multimodal Depth Completion Model

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal information requires more network modules to process different modalities. But the application scenarios of sparse ToF measurements usually demand lightweight structure and low computational cost. Second, fusing sparse and noisy depth data with dense pixel-wise RGB data may introduce artifacts. In this paper, a light but efficient depth completion network is proposed, which consists of a two-branch global and local depth prediction module and a funnel convolutional spatial propagation network. The two-branch structure extracts and fuses cross-modal features with lightweight backbones. The improved spatial propagation module can refine the completed depth map gradually. Furthermore, corrected gradient loss is presented for the depth completion problem. Experimental results demonstrate the proposed method can outperform some state-of-the-art methods with a lightweight architecture. The proposed method also wins the championship in the MIPI2022 RGB+TOF depth completion challenge.

cs.CV↗

arXiv2022

A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation

Reliable navigation systems have a wide range of applications in robotics and autonomous driving. Current approaches employ an open-loop process that converts sensor inputs directly into actions. However, these open-loop schemes are challenging to handle complex and dynamic real-world scenarios due to their poor generalization. Imitating human navigation, we add a reasoning process to convert actions back to internal latent states, forming a two-stage closed loop of perception, decision-making, and reasoning. Firstly, VAE-Enhanced Demonstration Learning endows the model with the understanding of basic navigation rules. Then, two dual processes in RL-Enhanced Interaction Learning generate reward feedback for each other and collectively enhance obstacle avoidance capability. The reasoning model can substantially promote generalization and robustness, and facilitate the deployment of the algorithm to real-world robots without elaborate transfers. Experiments show our method is more adaptable to novel scenarios compared with state-of-the-art approaches.

cs.RO↗

arXiv2022

Fractional Vegetation Cover Estimation using Hough Lines and Linear Iterative Clustering

A common requirement of plant breeding programs across the country is companion planting -- growing different species of plants in close proximity so they can mutually benefit each other. However, the determination of companion plants requires meticulous monitoring of plant growth. The technique of ocular monitoring is often laborious and error prone. The availability of image processing techniques can be used to address the challenge of plant growth monitoring and provide robust solutions that assist plant scientists to identify companion plants. This paper presents a new image processing algorithm to determine the amount of vegetation cover present in a given area, called fractional vegetation cover. The proposed technique draws inspiration from the trusted Daubenmire method for vegetation cover estimation and expands upon it. Briefly, the idea is to estimate vegetation cover from images containing multiple rows of plant species growing in close proximity separated by a multi-segment PVC frame of known size. The proposed algorithm applies a Hough Transform and Simple Linear Iterative Clustering (SLIC) to estimate the amount of vegetation cover within each segment of the PVC frame. The analysis when repeated over images captured at regular intervals of time provides crucial insights into plant growth. As a means of comparison, the proposed algorithm is compared with SamplePoint and Canopeo, two trusted applications used for vegetation cover estimation. The comparison shows a 99% similarity with both SamplePoint and Canopeo demonstrating the accuracy and feasibility of the algorithm for fractional vegetation cover estimation.

cs.CV↗

arXiv2022

Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining

Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases. Concretely, we introduce an intuitive geometric model which represents palmar creases with parameterized Bézier curves. By randomly sampling Bézier parameters, we can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability: they can be efficiently transferred to real datasets, leading to significant performance improvements on palmprint recognition. For example, under the open-set protocol, our method improves the strong ArcFace baseline by more than 10\% in terms of TAR@1e-6. And under the closed-set protocol, our method reduces the equal error rate (EER) by an order of magnitude.

cs.CV↗

arXiv2022

ContrastMask: Contrastive Learning to Segment Every Thing

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective class-agnostic mask segmentation model. Unlike previous methods that learn such models only on seen categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both seen and unseen categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.

cs.CV↗

arXiv2022

Nonlinear semigroup approach to Hamilton-Jacobi equations -- A toy model

In this paper, we discuss the existence and multiplicity problem of viscosity solution to the Hamilton-Jacobi equation $$h(x,d_x u)+λ(x)u=c,\quad x\in M,$$ where $M$ is a closed manifold and $λ:M\rightarrow\mathbb{R}$ changes signs on $M$, via nonlinear semigroup method. It turns out that a bifurcation phenomenon occurs when parameter $c$ strides over the critical value. As an application of the main result, we analyse the structure of the set of viscosity solutions of an one-dimensional example in detail.

math.AP↗

arXiv2022

SZx: an Ultra-fast Error-bounded Lossy Compressor for Scientific Datasets

Today's scientific high performance computing (HPC) applications or advanced instruments are producing vast volumes of data across a wide range of domains, which introduces a serious burden on data transfer and storage. Error-bounded lossy compression has been developed and widely used in scientific community, because not only can it significantly reduce the data volumes but it can also strictly control the data distortion based on the use-specified error bound. Existing lossy compressors, however, cannot offer ultra-fast compression speed, which is highly demanded by quite a few applications or use-cases (such as in-memory compression and online instrument data compression). In this paper, we propose a novel ultra-fast error-bounded lossy compressor, which can obtain fairly high compression performance on both CPU and GPU, also with reasonably high compression ratios. The key contributions are three-fold: (1) We propose a novel, generic ultra-fast error-bounded lossy compression framework -- called UFZ, by confining our design to be composed of only super-lightweight operations such as bitwise and addition/subtraction operation, still keeping a certain high compression ratio. (2) We implement UFZ on both CPU and GPU and optimize the performance according to their architectures carefully. (3) We perform a comprehensive evaluation with 6 real-world production-level scientific datasets on both CPU and GPU. Experiments show that UFZ is 2~16X as fast as the second-fastest existing error-bounded lossy compressor (either SZ or ZFP) on CPU and GPU, with respect to both compression and decompression.

cs.DC↗

arXiv2022

Variational attraction of the KAM torus for the conformally symplectic system

For the conformally symplectic system \[ \left\{ \begin{aligned} \dot{q}&=H_p(q,p),\quad(q,p)\in T^*\mathbb{T}^n\\ \dot p&=-H_q(q,p)-λp, \quad λ>0 \end{aligned} \right. \] with a positive definite Hamiltonian, we discuss the variational significance of invariant Lagrangian graphs and explain how the KAM torus impacts the $W^{1,\infty}-$convergence speed of the Lax-Oleinik semigroup.

math.DS↗

arXiv2021

Time-periodic solutions of contact Hamilton-Jacobi equations on the circle

We are concerned with the existence and multiplicity of nontrivial time-periodic viscosity solutions to \[ \partial_t w(x,t) + H( x,\partial_x w(x,t),w(x,t) )=0,\quad (x,t)\in \mathbb{S} \times [0,+\infty). \] We find that there are infinitely many nontrivial time-periodic viscosity solutions with different periods when $\frac{\partial H}{\partial u}(x,p,u)\leqslant-δ<0$ by analyzing the asymptotic behavior of the dynamical system $(C(\mathbb{S} ,\mathbb{R}),\{T_t\}_{t\geqslant 0})$, where $\{T_t\}_{t\geqslant 0}$ was introduced in \cite{WWY1}. Moreover, in view of the convergence of $T_{t_n}φ$, we get the existence of nontrivial periodic points of $T_t$, where $φ$ are initial data satisfying certain properties. This is a long-time behavior result for the solution to the above equation with initial data $φ$. At last, as an application, we describe to readers a bifurcation phenomenon for \[ \partial_t w(x,t) + H( x,\partial_x w(x,t),λw(x,t) )=0,\quad (x,t)\in \mathbb{S} \times [0,+\infty), \] when the sign of the parameter $λ$ varies. The structure of the unit circle $\mathbb{S}$ plays an essential role here. The most important novelty is the discovery of the nontrivial recurrence of $(C(\mathbb{S} ,\mathbb{R}),\{T_t\}_{t\geqslant 0})$.

math.AP↗

arXiv2021

The Levy Flight of Cities: Analyzing Social-Economical Trajectories with Auto-Embedding

It has been found that human mobility exhibits random patterns following the Levy flight, where human movement contains many short flights and some long flights, and these flights follow a power-law distribution. In this paper, we study the social-economical development trajectories of urban cities. We observe that social-economical movement of cities also exhibit the Levy flight characteristics. We collect the social and economical data such as the population, the number of students, GDP and personal income, etc. from several cities. Then we map these urban data into the social and economical factors through a deep-learning embedding method Auto-Encoder. We find that the social-economical factors of these cities can be fitted approximately as a movement pattern of a power-law distribution. We use the Stochastic Multiplicative Processes (SMP) to explain such movement, where in the presence of a boundary constraint, the SMP leads to a power law distribution. It means that the social-economical trajectories of cities also follow a Levy flight pattern, where some years have large changes in terms of social-economical development, and many years have little changes.

physics.soc-ph↗

arXiv2021

Learning to Navigate in a VUCA Environment: Hierarchical Multi-expert Approach

Despite decades of efforts, robot navigation in a real scenario with volatility, uncertainty, complexity, and ambiguity (VUCA for short), remains a challenging topic. Inspired by the central nervous system (CNS), we propose a hierarchical multi-expert learning framework for autonomous navigation in a VUCA environment. With a heuristic exploration mechanism considering target location, path cost, and safety level, the upper layer performs simultaneous map exploration and route-planning to avoid trapping in a blind alley, similar to the cerebrum in the CNS. Using a local adaptive model fusing multiple discrepant strategies, the lower layer pursuits a balance between collision-avoidance and go-straight strategies, acting as the cerebellum in the CNS. We conduct simulation and real-world experiments on multiple platforms, including legged and wheeled robots. Experimental results demonstrate our algorithm outperforms the existing methods in terms of task achievement, time efficiency, and security.

cs.RO↗

arXiv2021

SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors

Today's scientific simulations require a significant reduction of data volume because of extremely large amounts of data they produce and the limited I/O bandwidth and storage space. Error-bounded lossy compressor has been considered one of the most effective solutions to the above problem. In practice, however, the best-fit compression method often needs to be customized/optimized in particular because of diverse characteristics in different datasets and various user requirements on the compression quality and performance. In this paper, we develop a novel modular, composable compression framework (namely SZ3), which involves three significant contributions. (1) SZ3 features a modular abstraction for the prediction-based compression framework such that the new compression modules can be plugged in easily. (2) SZ3 supports multialgorithm predictors and can automatically select the best-fit predictor for each data block based on the designed error estimation criterion. (3) SZ3 allows users to easily compose different compression pipelines on demand, such that both compression quality and performance can be significantly improved for their specific datasets and requirements. (4) In addition, we evaluate several lossy compressors composed from SZ3 using the real-world datasets. Specifically, we leverage SZ3 to improve the compression quality and performance for different use-cases, including GAMESS quantum chemistry dataset and Advanced Photon Source (APS) instrument dataset. Experiments show that our customized compression pipelines lead to up to 20% improvement in compression ratios under the same data distortion compared with the state-of-the-art approaches.

cs.DC↗

arXiv2021

FakeMix Augmentation Improves Transparent Object Detection

Detecting transparent objects in natural scenes is challenging due to the low contrast in texture, brightness and colors. Recent deep-learning-based works reveal that it is effective to leverage boundaries for transparent object detection (TOD). However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability. Detailly, a kind of boundaries in the background, which share the same characteristics with boundaries of transparent objects but have much smaller amounts, usually hurt the performance. To conquer the boundary-related imbalance problem, we propose a novel content-dependent data augmentation method termed FakeMix. Considering collecting these trouble-maker boundaries in the background is hard without corresponding annotations, we elaborately generate them by appending the boundaries of transparent objects from other samples into the current image during training, which adjusts the data space and improves the generalization of the models. Further, we present AdaptiveASPP, an enhanced version of ASPP, that can capture multi-scale and cross-modality features dynamically. Extensive experiments demonstrate that our methods clearly outperform the state-of-the-art methods. We also show that our approach can also transfer well on related tasks, in which the model meets similar troubles, such as mirror detection, glass detection, and camouflaged object detection. Code will be made publicly available.

cs.CV↗

arXiv2021

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effectively representing and utilizing complementary features from the frame domain and event domain for boosting object tracking performance in challenge scenarios. Specifically, we propose Common Features Extractor (CFE) to learn potential common representations from the RGB domain and event domain. For learning the unique features of the two domains, we utilize a Unique Extractor for Event (UEE) based on Spiking Neural Networks to extract edge cues in the event domain which may be missed in RGB in some challenging conditions, and a Unique Extractor for RGB (UER) based on Deep Convolutional Neural Networks to extract texture and semantic information in RGB domain. Extensive experiments on standard RGB benchmark and real event tracking dataset demonstrate the effectiveness of the proposed approach. We show our approach outperforms all compared state-of-the-art tracking algorithms and verify event-based data is a powerful cue for tracking in challenging scenes.

cs.CV↗

arXiv2021

Optimizing Error-Bounded Lossy Compression for Scientific Data on GPUs

Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes. With ever-emerging heterogeneous high-performance computing (HPC) architecture, GPU-accelerated error-bounded compressors (such as cuSZ+ and cuZFP) have been developed. However, they suffer from either low performance or low compression ratios. To this end, we propose cuSZ+ to target both high compression ratios and throughputs. We identify that data sparsity and data smoothness are key factors for high compression throughputs. Our key contributions in this work are fourfold: (1) We propose an efficient compression workflow to adaptively perform run-length encoding and/or variable-length encoding. (2) We derive Lorenzo reconstruction in decompression as multidimensional partial-sum computation and propose a fine-grained Lorenzo reconstruction algorithm for GPU architectures. (3) We carefully optimize each of cuSZ+ kernels by leveraging state-of-the-art CUDA parallel primitives. (4) We evaluate cuSZ+ using seven real-world HPC application datasets on V100 and A100 GPUs. Experiments show cuSZ+ improves the compression throughputs and ratios by up to 18.4X and 5.3X, respectively, over cuSZ on the tested datasets.

cs.DC↗

arXiv2021

Adaptive Feature Alignment for Adversarial Training

Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of accuracy, raising the contradiction between standard and adversarial accuracies. In this paper, we observe an interesting phenomenon that feature statistics change monotonically and smoothly w.r.t the rising of attacking strength. Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength. This is done by predicting a fusing weight in a dual-BN architecture. Unlike previous works that need to either retrain the model or manually tune a hyper-parameters for different attacking strengths, our method can deal with arbitrary attacking strengths with a single model without introducing any hyper-parameter. Importantly, our method improves the model robustness against adversarial samples without incurring much loss in standard accuracy. Experiments on CIFAR-10, SVHN, and tiny-ImageNet datasets demonstrate that our method outperforms the state-of-the-art under a wide range of attacking strengths.

cs.CV↗

arXiv2021

Development of Gated Fiber Detectors for Laser-Induced Strong Electromagnetic Pulse Environments

With the development of laser technologies, nuclear reactions can happen in high-temperature plasma environments induced by lasers and have attracted a lot of attention from different physical disciplines. However, studies on nuclear reactions in plasma are still limited by detecting technologies. This is mainly due to the fact that extremely high electromagnetic pulses (EMPs) can also be induced when high-intensity lasers hit targets to induce plasma, and then cause dysfunction of many types of traditional detectors. Therefore, new particle detecting technologies are highly needed. In this paper, we report a recently developed gated fiber detector which can be used in harsh EMP environments. In this prototype detector, scintillating photons are coupled by fiber and then transferred to a gated photomultiplier tube which is located far away from the EMP source and shielded well. With those measures, the EMPs can be avoided, and this device has the capability to identify a single event of nuclear reaction products generated in laser-induced plasma from noise EMP backgrounds. This new type of detector can be widely used as a Time-of-Flight (TOF) detector in high-intensity laser nuclear physics experiments for detecting neutron, photons, and other charged particles.

physics.ins-det↗

arXiv2021

Global propagation of singularities for discounted Hamilton-Jacobi equations

The main purpose of this paper is to study the global propagation of singularities of viscosity solution to discounted Hamilton-Jacobi equation \begin{equation}\label{eq:discount 1}\tag{HJ$_λ$} λv(x)+H( x, Dv(x) )=0 , \quad x\in \mathbb{R}^n. \end{equation} We reduce the problem for equation \eqref{eq:discount 1} into that for a time-dependent evolutionary Hamilton-Jacobi equation. We proved that the singularities of the viscosity solution of \eqref{eq:discount 1} propagate along locally Lipschitz singular characteristics which can extend to $+\infty$. We also obtained the homotopy equivalence between the singular set and the complement of associated the Aubry set with respect to the viscosity solution of equation \eqref{eq:discount 1}.

math.DS↗