arXiv subjects

Hanlin Chen

Publications and source records attributed to Hanlin Chen.

34 records · Page 2Linked to original sources

arXiv2024

GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields

Recent advancements in vision-language foundation models have significantly enhanced open-vocabulary 3D scene understanding. However, the generalizability of existing methods is constrained due to their framework designs and their reliance on 3D data. We address this limitation by introducing Generalizable Open-Vocabulary Neural Semantic Fields (GOV-NeSF), a novel approach offering a generalizable implicit representation of 3D scenes with open-vocabulary semantics. We aggregate the geometry-aware features using a cost volume, and propose a Multi-view Joint Fusion module to aggregate multi-view features through a cross-view attention mechanism, which effectively predicts view-specific blending weights for both colors and open-vocabulary features. Remarkably, our GOV-NeSF exhibits state-of-the-art performance in both 2D and 3D open-vocabulary semantic segmentation, eliminating the need for ground truth semantic labels or depth priors, and effectively generalize across scenes and datasets without fine-tuning.

cs.CV↗

arXiv2023

GNeSF: Generalizable Neural Semantic Fields

3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits generalization to novel scenes during inference. To circumvent this problem, we introduce a generalizable 3D segmentation framework based on implicit representation. Specifically, our framework takes in multi-view image features and semantic maps as the inputs instead of only spatial information to avoid overfitting to scene-specific geometric and semantic information. We propose a novel soft voting mechanism to aggregate the 2D semantic information from different views for each 3D point. In addition to the image features, view difference information is also encoded in our framework to predict the voting scores. Intuitively, this allows the semantic information from nearby views to contribute more compared to distant ones. Furthermore, a visibility module is also designed to detect and filter out detrimental information from occluded views. Due to the generalizability of our proposed method, we can synthesize semantic maps or conduct 3D semantic segmentation for novel scenes with solely 2D semantic supervision. Experimental results show that our approach achieves comparable performance with scene-specific approaches. More importantly, our approach can even outperform existing strong supervision-based approaches with only 2D annotations. Our source code is available at: https://github.com/HLinChen/GNeSF.

cs.CV↗

arXiv2023

DCA: Delayed Charging Attack on the Electric Shared Mobility System

An efficient operation of the electric shared mobility system (ESMS) relies heavily on seamless interconnections among shared electric vehicles (SEV), electric vehicle supply equipment (EVSE), and the grid. Nevertheless, this interconnectivity also makes the ESMS vulnerable to cyberattacks that may cause short-term breakdowns or long-term degradation of the ESMS. This study focuses on one such attack with long-lasting effects, the Delayed Charge Attack (DCA), that stealthily delays the charging service by exploiting the physical and communication vulnerabilities. To begin, we present the ESMS threat model by highlighting the assets, information flow, and access points. We next identify a linked sequence of vulnerabilities as a viable attack vector for launching DCA. Then, we detail the implementation of DCA, which can effectively bypass the detection in the SEV's battery management system and the cross-verification in the cloud environment. We test the DCA model against various Anomaly Detection (AD) algorithms by simulating the DCA dynamics in a Susceptible-Infectious-Removed-Susceptible process, where the EVSE can be compromised by the DCA or detected for repair. Using real-world taxi trip data and EVSE locations in New York City, the DCA model allows us to explore the long-term impacts and validate the system consequences. The results show that a 10-min delay results in 12-min longer queuing times and 8% more unfulfilled requests, leading to a 10.7% (\$311.7) weekly revenue loss per driver. With the AD algorithms, the weekly revenue loss remains at least 3.8% (\$111.8) with increased repair costs of \$36,000, suggesting the DCA's robustness against the AD.

cs.CR↗

arXiv2023

Note on VDB Topological Indices of k-Cyclic Graphs

Let $G$ be a connected graph with $n$ vertices and $m$ edges. The vertex-degree-based topological index (VDB) (or graphical function-index) $TI(G)$ of $G$ with edge-weight function $I(x,y)$ is defined as $$TI(G)=\sum\limits_{uv\in E(G)}I(d_{u},d_{v}),$$ where $I(x,y)>0$ is a symmetric real function with $x\geq 1$ and $y\geq 1$, $d_{u}$ is the degree of vertex $u$ in $G$. In this note, we deduce a number of previously established results, and state a few new. For a VDB topological index $TI$ with the property $P^{*}$, we can obtain the minimum $k$-cyclic (chemical) graphs for $k\geq3$, $n\geq 5(k-1)$. These VDB topological indices include the Sombor index, the general Sombor index, the $p$-Sombor index, the general sum-connectivity index and so on. Thus this note extends the results of Liu et al. [H. Liu, L. You, Y. Huang, Sombor index of c-cyclic chemical graphs, MATCH Commun. Math. Comput. Chem. 90 (2023) 495-504] and Ali et al. [A. Ali, D. Dimitrov, Z. Du, F. Ishfaq, On the extremal graphs for general sum-connectivity index $(χ_α)$ with given cyclomatic number when $α>1$, Discrete Appl. Math. 257 (2019) 19-30].

math.GM↗

arXiv2023

Improving Autonomous Vehicle Mapping and Navigation in Work Zones Using Crowdsourcing Vehicle Trajectories

Prevalent solutions for Connected and Autonomous vehicle (CAV) mapping include high definition map (HD map) or real-time Simultaneous Localization and Mapping (SLAM). Both methods only rely on vehicle itself (onboard sensors or embedded maps) and can not adapt well to temporarily changed drivable areas such as work zones. Navigating CAVs in such areas heavily relies on how the vehicle defines drivable areas based on perception information. Difficulties in improving perception accuracy and ensuring the correct interpretation of perception results are challenging to the vehicle in these situations. This paper presents a prototype that introduces crowdsourcing trajectories information into the mapping process to enhance CAV's understanding on the drivable area and traffic rules. A Gaussian Mixture Model (GMM) is applied to construct the temporarily changed drivable area and occupancy grid map (OGM) based on crowdsourcing trajectories. The proposed method is compared with SLAM without any human driving information. Our method has adapted well with the downstream path planning and vehicle control module, and the CAV did not violate driving rule, which a pure SLAM method did not achieve.

cs.RO↗

arXiv2022

A Cooperative Perception Environment for Traffic Operations and Control

Existing data collection methods for traffic operations and control usually rely on infrastructure-based loop detectors or probe vehicle trajectories. Connected and automated vehicles (CAVs) not only can report data about themselves but also can provide the status of all detected surrounding vehicles. Integration of perception data from multiple CAVs as well as infrastructure sensors (e.g., LiDAR) can provide richer information even under a very low penetration rate. This paper aims to develop a cooperative data collection system, which integrates Lidar point cloud data from both infrastructure and CAVs to create a cooperative perception environment for various transportation applications. The state-of-the-art 3D detection models are applied to detect vehicles in the merged point cloud. We test the proposed cooperative perception environment with the max pressure adaptive signal control model in a co-simulation platform with CARLA and SUMO. Results show that very low penetration rates of CAV plus an infrastructure sensor are sufficient to achieve comparable performance with 30% or higher penetration rates of connected vehicles (CV). We also show the equivalent CV penetration rate (E-CVPR) under different CAV penetration rates to demonstrate the data collection efficiency of the cooperative perception environment.

cs.RO↗

arXiv2021

On the first three minimum Mostar indices of tree-like phenylenes

Let $G =(V_{G}, E_{G})$ be a simple connected graph with its vertex set $V_{G}$ and edge set $E_{G}$. The Mostar index $Mo(G)$ was defined as $Mo(G)=\sum\limits_{e=uv\in E(G)}|n_{u}-n_{v}|$, where $n_{u}$ (resp., $n_{v}$) is the number of vertices whose distance to vertex $u$ (resp., $v$) is smaller than the distance to vertex $v$ (resp., $u$). In this study, we determine the first three minimum Mostar indices of tree-like phenylenes and characterize all the tree-like phenylenes attaining these values. At last, we give some numerical examples and discussion.

math.CO↗

arXiv2020

Binarized Neural Architecture Search for Efficient Object Recognition

Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing. The BNAS calculation is more challenging than NAS due to the learning inefficiency caused by optimization requirements and the huge architecture space, and the performance loss when handling the wild data in various computing applications. To address these issues, we introduce operation space reduction and channel sampling into BNAS to significantly reduce the cost of searching. This is accomplished through a performance-based strategy that is robust to wild data, which is further used to abandon less potential operations. Furthermore, we introduce the Upper Confidence Bound (UCB) to solve 1-bit BNAS. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a comparable performance to NAS on both CIFAR and ImageNet databases. An accuracy of $96.53\%$ vs. $97.22\%$ is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a $40\%$ faster search than the state-of-the-art PC-DARTS. On the wild face recognition task, our binarized models achieve a performance similar to their corresponding full-precision models.

cs.CV↗

arXiv2020

Anti-Bandit Neural Architecture Search for Model Defense

Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks. In this paper, we defend against adversarial attacks using neural architecture search (NAS) which is based on a comprehensive search of denoising blocks, weight-free operations, Gabor filters and convolutions. The resulting anti-bandit NAS (ABanditNAS) incorporates a new operation evaluation measure and search process based on the lower and upper confidence bounds (LCB and UCB). Unlike the conventional bandit algorithm using UCB for evaluation only, we use UCB to abandon arms for search efficiency and LCB for a fair competition between arms. Extensive experiments demonstrate that ABanditNAS is faster than other NAS methods, while achieving an $8.73\%$ improvement over prior arts on CIFAR-10 under PGD-$7$.

cs.CV↗

arXiv2020

Cogradient Descent for Bilinear Optimization

Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure. One reason lies in the insufficient training due to the asynchronous gradient descent, which results in vanishing gradients for the coupled variables. In this paper, we introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem, based on a theoretical framework to coordinate the gradient of hidden variables via a projection function. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent to facilitate the optimization procedure. Our algorithm is applied to solve problems with one variable under the sparsity constraint, which is widely used in the learning paradigm. We validate our CoGD considering an extensive set of applications including image reconstruction, inpainting, and network pruning. Experiments show that it improves the state-of-the-art by a significant margin.

cs.CV↗

arXiv2020

CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks

Neural architecture search (NAS) proves to be among the best approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same time, 1-bit convolutional neural networks (CNNs) with binarized weights and activations show their potential for resource-limited embedded devices. One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework. To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent). In the search stage, the Child-Parent model uses an indicator generated by the child and parent model accuracy to evaluate the performance and abandon operations with less potential. In the training stage, a kernel-level CP loss is introduced to optimize the binarized network. Extensive experiments demonstrate that the proposed CP-NAS achieves a comparable accuracy with traditional NAS on both the CIFAR and ImageNet databases. It achieves the accuracy of $95.27\%$ on CIFAR-10, $64.3\%$ on ImageNet with binarized weights and activations, and a $30\%$ faster search than prior arts.

cs.CV↗

arXiv2020

Binarized Neural Architecture Search

Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models. Unfortunately, this area remains largely unexplored. BNAS is more challenging than NAS due to the learning inefficiency caused by optimization requirements and the huge architecture space. To address these issues, we introduce channel sampling and operation space reduction into a differentiable NAS to significantly reduce the cost of searching. This is accomplished through a performance-based strategy used to abandon less potential operations. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a performance comparable to NAS on both CIFAR and ImageNet databases. An accuracy of $96.53\%$ vs. $97.22\%$ is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a $40\%$ faster search than the state-of-the-art PC-DARTS.

cs.CV↗

arXiv2017

Bounds on some monotonic topological indices of bipartite graphs with a given number of cut edges

Let $I(G)$ be a topological index of a graph. If $I(G+e) I(G)$, respectively) for each edge $e\not\in G$, then $I(G)$ is monotonically decreasing (or increasing, respectively) with the addition of edges. In this article, we present lower or upper bounds for some monotonic topological indices, including the Wiener index, the hyper-Wiener index, the Harary index, the connective eccentricity index, the eccentricity distance sum of bipartite graphs in terms of the number of cut edges, and characterize the corresponding extremal graphs, respectively.

math.CO↗

arXiv2014

Dimer-monomer Model on the Towers of Hanoi Graphs

The number of dimer-monomers (matchings) of a graph $G$ is an important graph parameter in statistical physics. Following recent research, we study the asymptotic behavior of the number of dimer-monomers $m(G)$ on the Towers of Hanoi graphs and another variation of the Sierpiński graphs which is similar to the Towers of Hanoi graphs, and derive the recursion relations for the numbers of dimer-monomers. Upper and lower bounds for the entropy per site, defined as $μ_{G}=\lim_{v(G)\rightarrow\infty}\frac{\ln m(G)}{v(G)}$, where $v(G)$ is the number of vertices in a graph $G$, on these Sierpiński graphs are derived in terms of the numbers at a certain stage. As the difference between these bounds converges quickly to zero as the calculated stage increases, the numerical value of the entropy can be evaluated with more than a hundred significant figures accuracy.

math-ph↗

arXiv2014

Tutte polynomial of a fractal scale-free lattice

The Tutte polynomial of a graph, or equivalently the $q$-state Potts model partition function, is a two-variable polynomial graph invariant of considerable importance in both combinatorics and statistical physics. The computation of this invariant for a graph is NP-hard in general. In this paper, based on their self-similar structures, we recursively describe the Tutte polynomials of an infinite family of scale-free lattices. Furthermore, we give some exact analytical expressions of the Tutte polynomial for several special points at $(X,Y)$-plane.

math.CO↗

arXiv2004

Hidden symmetries in primary sequences of small alpha proteins

Proteins have regular tertiary structures but irregular amino acid sequences. This made it very difficult to decode the structural information in the protein sequences. Here we demonstrate that many small alpha protein domains have hidden sequence symmetries characteristic of their pseudo-symmetric tertiary structures. We also present a modified method of recurrent plot to reveal this kind of the hidden sequence symmetry. The results may enable us understand parts of the relations between protein sequences and their tertiary structures, i.e, how the primary sequence of a protein determines its tertiary structure.

q-bio.BM↗