arXiv subjects

Fei Hu

Publications and source records attributed to Fei Hu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

6D Object Pose Estimation is a crucial yet challenging task in computer vision, suffering from a significant lack of large-scale datasets. This scarcity impedes comprehensive evaluation of model performance, limiting research advancements. Furthermore, the restricted number of available instances or categories curtails its applications. To address these issues, this paper introduces Omni6DPose, a substantial dataset characterized by its diversity in object categories, large scale, and variety in object materials. Omni6DPose is divided into three main components: ROPE (Real 6D Object Pose Estimation Dataset), which includes 332K images annotated with over 1.5M annotations across 581 instances in 149 categories; SOPE(Simulated 6D Object Pose Estimation Dataset), consisting of 475K images created in a mixed reality setting with depth simulation, annotated with over 5M annotations across 4162 instances in the same 149 categories; and the manually aligned real scanned objects used in both ROPE and SOPE. Omni6DPose is inherently challenging due to the substantial variations and ambiguities. To address this challenge, we introduce GenPose++, an enhanced version of the SOTA category-level pose estimation framework, incorporating two pivotal improvements: Semantic-aware feature extraction and Clustering-based aggregation. Moreover, we provide a comprehensive benchmarking analysis to evaluate the performance of previous methods on this large-scale dataset in the realms of 6D object pose estimation and pose tracking.

cs.CV↗

arXiv2023

Canonical heights for abelian group actions of maximal dynamical rank

Let $X$ be a smooth projective variety of dimension $n\geq 2$ and $G\cong\mathbf{Z}^{n-1}$ a free abelian group of automorphisms of $X$ over $\overline{\mathbf{Q}}$. Suppose that $G$ is of positive entropy. We construct a canonical height function $\widehat{h}_G$ associated with $G$, corresponding to a nef and big $\mathbf{R}$-divisor, satisfying the Northcott property. By characterizing its null locus, we prove the Kawaguchi--Silverman conjecture for each element of $G$. As another application, we determine the height counting function for non-periodic points.

math.NT↗

arXiv2023

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Human pose estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains, such as human-computer interaction, sports analysis, and human tracking via images and videos. Recently, deep learning-based approaches have shown state-of-the-art performance in HPE-based applications. Although deep learning-based approaches have achieved remarkable performance in HPE, a comprehensive review of deep learning-based HPE methods remains lacking in the literature. In this article, we provide an up-to-date and in-depth overview of the deep learning approaches in vision-based HPE. We summarize these methods of 2-D and 3-D HPE, and their applications, discuss the challenges and the research trends through bibliometrics, and provide insightful recommendations for future research. This article provides a meaningful overview as introductory material for beginners to deep learning-based HPE, as well as supplementary material for advanced researchers.

cs.CV↗

arXiv2023

A Dynamic Distributed Scheduler for Computing on the Edge

Edge computing has become a promising computing paradigm for building IoT (Internet of Things) applications, particularly for applications with specific constraints such as latency or privacy requirements. Due to resource constraints at the edge, it is important to efficiently utilize all available computing resources to satisfy these constraints. A key challenge in utilizing these computing resources is the scheduling of different computing tasks in a dynamically varying, highly hybrid computing environment. This paper described the design, implementation, and evaluation of a distributed scheduler for the edge that constantly monitors the current state of the computing infrastructure and dynamically schedules various computing tasks to ensure that all application constraints are met. This scheduler has been extensively evaluated with real-world AI applications under different scenarios and demonstrates that it outperforms current scheduling approaches in satisfying various application constraints.

cs.DC↗

arXiv2023

Polynomial volume growth of quasi-unipotent automorphisms of abelian varieties (with an appendix in collaboration with Chen Jiang)

Let $X$ be an abelian variety over an algebraically closed field $\mathbf{k}$ and $f$ a quasi-unipotent automorphism of $X$. When $\mathbf{k}$ is the field of complex numbers, Lin, Oguiso, and D.-Q. Zhang provide an explicit formula for the polynomial volume growth of (or equivalently, for the Gelfand--Kirillov dimension of the twisted homogeneous coordinate ring associated with) the pair $(X, f)$, by an analytic argument. We give an algebraic proof of this formula that works in arbitrary characteristic. In the course of the proof, we obtain: (1) a new description of the action of endomorphisms on the $\ell$-adic Tate spaces, in comparison with recent results of Zarhin and Poonen--Rybakov; (2) a partial converse to a result of Reichstein, Rogalski, and J.J. Zhang on quasi-unipotency of endomorphisms and their pullback action on the rational Néron--Severi space $\mathsf{N}^1(X)_{\mathbf{Q}}$ of $\mathbf{Q}$-divisors modulo numerical equivalence; (3) the maximum size of Jordan blocks of (the Jordan canonical form of) $f^*|_{\mathsf{N}^1(X)_{\mathbf{Q}}}$ in terms of the action of $f$ on the Tate space $V_\ell(X)$.

math.AG↗

arXiv2023

Concealed Object Detection for Passive Millimeter-Wave Security Imaging Based on Task-Aligned Detection Transformer

Passive millimeter-wave (PMMW) is a significant potential technique for human security screening. Several popular object detection networks have been used for PMMW images. However, restricted by the low resolution and high noise of PMMW images, PMMW hidden object detection based on deep learning usually suffers from low accuracy and low classification confidence. To tackle the above problems, this paper proposes a Task-Aligned Detection Transformer network, named PMMW-DETR. In the first stage, a Denoising Coarse-to-Fine Transformer (DCFT) backbone is designed to extract long- and short-range features in the different scales. In the second stage, we propose the Query Selection module to introduce learned spatial features into the network as prior knowledge, which enhances the semantic perception capability of the network. In the third stage, aiming to improve the classification performance, we perform a Task-Aligned Dual-Head block to decouple the classification and regression tasks. Based on our self-developed PMMW security screening dataset, experimental results including comparison with State-Of-The-Art (SOTA) methods and ablation study demonstrate that the PMMW-DETR obtains higher accuracy and classification confidence than previous works, and exhibits robustness to the PMMW images of low quality.

cs.CV↗

arXiv2023

AGConv: Adaptive Graph Convolution on 3D Point Clouds

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic limitation of poor distinctive feature learning. In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis. AGConv generates adaptive kernels for points according to their dynamically learned features. Compared with the solution of using fixed/isotropic kernels, AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike the popular attentional weight schemes, AGConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive evaluations clearly show that our method outperforms state-of-the-arts of point cloud classification and segmentation on various benchmark datasets.Meanwhile, AGConv can flexibly serve more point cloud analysis approaches to boost their performance. To validate its flexibility and effectiveness, we explore AGConv-based paradigms of completion, denoising, upsampling, registration and circle extraction, which are comparable or even superior to their competitors. Our code is available at https://github.com/hrzhou2/AdaptConv-master.

cs.CV↗

arXiv2022

SPCNet: Stepwise Point Cloud Completion Network

How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud completion task. We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings. SPCNet has a hierarchical bottom-to-up network architecture. It fulfills shape completion in an iterative manner, which 1) first infers the global feature of the coarse result; 2) then infers the local feature with the aid of global feature; and 3) finally infers the detailed result with the help of local feature and coarse result. Beyond the wisdom of simulating the physical repair, we newly design a cycle loss %based training strategy to enhance the generalization and robustness of SPCNet. Extensive experiments clearly show the superiority of our SPCNet over the state-of-the-art methods on 3D point clouds with large missings.

cs.CV↗

arXiv2022

Eigenvalues and dynamical degrees of self-maps on abelian varieties

Let $X$ be a smooth projective variety over an algebraically closed field, and $f\colon X\to X$ a surjective self-morphism of $X$. The $i$-th cohomological dynamical degree $χ_i(f)$ is defined as the spectral radius of the pullback $f^{*}$ on the étale cohomology group $H^i_{\textrm{ét}}(X, \mathbf{Q}_\ell)$ and the $k$-th numerical dynamical degree $λ_k(f)$ as the spectral radius of the pullback $f^{*}$ on the vector space $\mathsf{N}^k(X)_{\mathbf{R}}$ of real algebraic cycles of codimension $k$ on $X$ modulo numerical equivalence. Truong conjectured that $χ_{2k}(f) = λ_k(f)$ for all $0 \le k \le \dim X$ as a generalization of Weil's Riemann hypothesis. We prove this conjecture in the case of abelian varieties. In the course of the proof we also obtain a new parity result on the eigenvalues of self-maps of abelian varieties in prime characteristic, which is of independent interest.

math.AG↗

arXiv2021

A dynamical approach to generalized Weil's Riemann hypothesis and semisimplicity

Let $X$ be a smooth projective variety over an algebraically closed field of arbitrary characteristic, and $f$ a dynamical correspondence of $X$. In 2016, the second author conjectured that the dynamical degrees of $f$ defined by the pullback actions on étale cohomology groups and on numerical cycle class groups are equivalent, which we call the dynamical degree comparison (DDC) conjecture. It contains the generalized Weil's Riemann hypothesis (for polarized endomorphisms) as a special case. To proceed, we introduce the so-called Conjecture $G_r$, which is a quantitative strengthening of the standard conjecture $C$ and holds on abelian varieties and Kummer surfaces. We prove that for arbitrary varieties, Conjecture $G_r$ yields the generalized Weil's Riemann hypothesis. Moreover, Conjecture $G_r$ plus the standard conjecture $D$ imply the so-called norm comparison (NC) conjecture, whose consequences include the DDC conjecture and the generalized semisimplicity conjecture (for polarized endomorphisms). As an application, we obtain new results on the DDC conjecture for abelian varieties and Kummer surfaces, and the generalized semisimplicity conjecture for Kummer surfaces. Finally, we also obtain a similar comparison result for effective finite correspondences of abelian varieties.

math.AG↗

arXiv2021

A Novel Optimized Asynchronous Federated Learning Framework

Federated Learning (FL) since proposed has been applied in many fields, such as credit assessment, medical, etc. Because of the difference in the network or computing resource, the clients may not update their gradients at the same time that may take a lot of time to wait or idle. That's why Asynchronous Federated Learning (AFL) method is needed. The main bottleneck in AFL is communication. How to find a balance between the model performance and the communication cost is a challenge in AFL. This paper proposed a novel AFL framework VAFL. And we verified the performance of the algorithm through sufficient experiments. The experiments show that VAFL can reduce the communication times about 51.02\% with 48.23\% average communication compression rate and allow the model to be converged faster. The code is available at \url{https://github.com/RobAI-Lab/VAFL}

cs.LG↗

arXiv2021

Densely connected neural networks for nonlinear regression

Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimension of proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation (0.91) with observations, which indicates that our model could advance environmental data analysis.

cs.LG↗

arXiv2021

FastSeq: Make Sequence Generation Faster

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop FastSeq framework to accelerate sequence generation without accuracy loss. The proposed optimization techniques include an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O. These optimizations are general enough to be applicable to Transformer-based models (e.g., T5, GPT2, and UniLM). Our benchmark results on a set of widely used and diverse models demonstrate 4-9x inference speed gain. Additionally, FastSeq is easy to use with a simple one-line code change. The source code is available at https://github.com/microsoft/fastseq.

cs.CL↗

arXiv2021

An inequality on polarized endomorphisms

We show that assuming the standard conjectures, for any smooth projective variety $X$ of dimension $n$ over an algebraically closed field, there is a constant $C>0$ such that for any positive rational number $r$ and for any polarized endomorphism $f$ of $X$, we have \[ \| G_r \circ f \| \le C \, \mathrm{deg}(G_r \circ f), \] where $G_r$ is a correspondence of $X$ so that for each $0\le i\le 2n$ its pullback action on the $i$-th Weil cohomology group is the multiplication-by-$r^i$ map. This inequality has been conjectured by the authors to hold in a more general setting, which - in the special case of polarized endomorphisms - confirms the validity of the analog of a well known result by Serre in the Kähler setting.

math.AG↗

arXiv2020

QoE-Driven UAV-Enabled Pseudo-Analog Wireless Video Broadcast: A Joint Optimization of Power and Trajectory

The explosive demands for high quality mobile video services have caused heavy overload to the existing cellular networks. Although the small cell has been proposed to alleviate such a problem, the network operators may not be interested in deploying numerous base stations (BSs) due to expensive infrastructure construction and maintenance. The unmanned aerial vehicles (UAVs) can provide the low-cost and quick deployment, which can support high-quality line-of-sight communications and have become promising mobile BSs. In this paper, we propose a quality-of-experience (QoE)-driven UAV-enabled pseudo-analog wireless video broadcast scheme, which provides mobile video broadcast services for ground users (GUs). Due to limited energy available in UAV, the aim of the proposed scheme is to maximize the minimum peak signal-to-noise ratio (PSNR) of GUs' video reconstruction quality by jointly optimizing the transmission power allocation strategy and the UAV trajectory. Firstly, the reconstructed video quality at GUs is defined under the constraints of the UAV's total energy and motion mechanism, and the proposed scheme is formulated as a complex non-convex optimization problem. Then, the optimization problem is simplified to obtain a tractable suboptimal solution with the help of the block coordinate descent model and the successive convex approximation model. Finally, the experimental results are presented to show the effectiveness of the proposed scheme. Specifically, the proposed scheme can achieve over 1.6dB PSNR gains in terms of GUs' minimum PSNR, compared with the state-of-the-art schemes, e.g., DVB, SoftCast, and SharpCast.

cs.MM↗

arXiv2020

Human-Perception-Oriented Pseudo Analog Video Transmissions with Deep Learning

Recently, pseudo analog transmission has gained increasing attentions due to its ability to alleviate the cliff effect in video multicast scenarios. The existing pseudo analog systems are sorely optimized under the minimum mean squared error criterion without taking the perceptual video quality into consideration. In this paper, we propose a human-perception-based pseudo analog video transmission system named ROIC-Cast, which aims to intelligently enhance the transmission quality of the region-of-interest (ROI) parts. Firstly, the classic deep learning based saliency detection algorithm is adopted to decompose the continuous video sequences into ROI and non-ROI blocks. Secondly, an effective compression method is used to reduce the data amount of side information generated by the ROI extraction module. Then, the power allocation scheme is formulated as a convex problem, and the optimal transmission power for both ROI and non-ROI blocks is derived in a closed form. Finally, the simulations are conducted to validate the proposed system by comparing with a few of existing systems, e.g., KMV-Cast, SoftCast, and DAC-RAN. The proposed ROIC-Cast can achieve over 4.1dB peak signal- to-noise ratio gains of ROI compared with other systems, given the channel signal-to-noise ratio as -5dB, 0dB, 5dB, and 10dB, respectively. This significant performance improvement is due to the automatic ROI extraction, high-efficiency data compression as well as adaptive power allocation.

cs.MM↗

arXiv2020

Free abelian group actions on normal projective varieties: sub-maximal dynamical rank case

Let $X$ be a normal projective variety of dimension $n$ and $G$ an abelian group of automorphisms such that all elements of $G\setminus \{\mathrm{id}\}$ are of positive entropy. Dinh and Sibony showed that $G$ is actually free abelian of rank $\le n - 1$. The maximal rank case has been well understood by De-Qi Zhang. We aim to characterize the pair $(X, G)$ such that $\mathrm{rank} G = n - 2$.

math.AG↗

arXiv2020

Height Gap Conjectures, $D$-Finiteness, and Weak Dynamical Mordell-Lang

In previous work, the first author, Ghioca, and the third author introduced a broad dynamical framework giving rise to many classical sequences from number theory and algebraic combinatorics. Specifically, these are sequences of the form $f(Φ^n(x))$, where $Φ\colon X\to X$ and $f\colon X\to\mathbb{P}^1$ are rational maps defined over $\overline{\mathbb{Q}}$ and $x\in X(\overline{\mathbb{Q}})$ is a point whose forward orbit avoids the indeterminacy loci of $Φ$ and $f$. They conjectured that if the sequence is infinite, then $\limsup \frac{h(f(Φ^n(x)))}{\log n} > 0$. They also made a corresponding conjecture for $\liminf$ and showed that it implies the Dynamical Mordell-Lang Conjecture. In this paper, we prove the $\limsup$ conjecture as well as the $\liminf$ conjecture away from a set of density $0$. As applications, we prove results concerning the growth rate of coefficients of $D$-finite power series as well as the Dynamical Mordell-Lang Conjecture up to a set of density $0$.

math.NT↗