Searcharxiv⌕ Search

arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 505 records · Page 28Linked to original sources
arXiv2023

StairNetV3: Depth-aware Stair Modeling using Deep Learning

Vision-based stair perception can help autonomous mobile robots deal with the challenge of climbing stairs, especially in unfamiliar environments. To address the problem that current monocular vision methods are difficult to model stairs accurately without depth information, this paper proposes a depth-aware stair modeling method for monocular vision. Specifically, we take the extraction of stair geometric features and the prediction of depth images as joint tasks in a convolutional neural network (CNN), with the designed information propagation architecture, we can achieve effective supervision for stair geometric feature learning by depth information. In addition, to complete the stair modeling, we take the convex lines, concave lines, tread surfaces and riser surfaces as stair geometric features and apply Gaussian kernels to enable the network to predict contextual information within the stair lines. Combined with the depth information obtained by depth sensors, we propose a stair point cloud reconstruction method that can quickly get point clouds belonging to the stair step surfaces. Experiments on our dataset show that our method has a significant improvement over the previous best monocular vision method, with an intersection over union (IOU) increase of 3.4 %, and the lightweight version has a fast detection speed and can meet the requirements of most real-time applications. Our dataset is available at https://data.mendeley.com/datasets/6kffmjt7g2/1.

cs.CV↗
arXiv2023

Digging into Depth Priors for Outdoor Neural Radiance Fields

Neural Radiance Fields (NeRF) have demonstrated impressive performance in vision and graphics tasks, such as novel view synthesis and immersive reality. However, the shape-radiance ambiguity of radiance fields remains a challenge, especially in the sparse viewpoints setting. Recent work resorts to integrating depth priors into outdoor NeRF training to alleviate the issue. However, the criteria for selecting depth priors and the relative merits of different priors have not been thoroughly investigated. Moreover, the relative merits of selecting different approaches to use the depth priors is also an unexplored problem. In this paper, we provide a comprehensive study and evaluation of employing depth priors to outdoor neural radiance fields, covering common depth sensing technologies and most application ways. Specifically, we conduct extensive experiments with two representative NeRF methods equipped with four commonly-used depth priors and different depth usages on two widely used outdoor datasets. Our experimental results reveal several interesting findings that can potentially benefit practitioners and researchers in training their NeRF models with depth priors. Project Page: https://cwchenwang.github.io/outdoor-nerf-depth

cs.CV↗
arXiv2023

AirVO: An Illumination-Robust Point-Line Visual Odometry

This paper proposes an illumination-robust visual odometry (VO) system that incorporates both accelerated learning-based corner point algorithms and an extended line feature algorithm. To be robust to dynamic illumination, the proposed system employs the convolutional neural network (CNN) and graph neural network (GNN) to detect and match reliable and informative corner points. Then point feature matching results and the distribution of point and line features are utilized to match and triangulate lines. By accelerating CNN and GNN parts and optimizing the pipeline, the proposed system is able to run in real-time on low-power embedded platforms. The proposed VO was evaluated on several datasets with varying illumination conditions, and the results show that it outperforms other state-of-the-art VO systems in terms of accuracy and robustness. The open-source nature of the proposed system allows for easy implementation and customization by the research community, enabling further development and improvement of VO for various applications.

cs.RO↗
arXiv2023

Primitive Skill-based Robot Learning from Human Evaluative Feedback

Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a novel framework, SEED, which leverages two approaches: reinforcement learning from human feedback (RLHF) and primitive skill-based reinforcement learning. Both approaches are particularly effective in addressing sparse reward issues and the complexities involved in long-horizon tasks. By combining them, SEED reduces the human effort required in RLHF and increases safety in training robot manipulation with RL in real-world settings. Additionally, parameterized skills provide a clear view of the agent's high-level intentions, allowing humans to evaluate skill choices before they are executed. This feature makes the training process even safer and more efficient. To evaluate the performance of SEED, we conducted extensive experiments on five manipulation tasks with varying levels of complexity. Our results show that SEED significantly outperforms state-of-the-art RL algorithms in sample efficiency and safety. In addition, SEED also exhibits a substantial reduction of human effort compared to other RLHF methods. Further details and video results can be found at https://seediros23.github.io/.

cs.RO↗
arXiv2023

FDCT: Fast Depth Completion for Transparent Objects

Depth completion is crucial for many robotic tasks such as autonomous driving, 3-D reconstruction, and manipulation. Despite the significant progress, existing methods remain computationally intensive and often fail to meet the real-time requirements of low-power robotic platforms. Additionally, most methods are designed for opaque objects and struggle with transparent objects due to the special properties of reflection and refraction. To address these challenges, we propose a Fast Depth Completion framework for Transparent objects (FDCT), which also benefits downstream tasks like object pose estimation. To leverage local information and avoid overfitting issues when integrating it with global information, we design a new fusion branch and shortcuts to exploit low-level features and a loss function to suppress overfitting. This results in an accurate and user-friendly depth rectification framework which can recover dense depth estimation from RGB-D images alone. Extensive experiments demonstrate that FDCT can run about 70 FPS with a higher accuracy than the state-of-the-art methods. We also demonstrate that FDCT can improve pose estimation in object grasping tasks. The source code is available at https://github.com/Nonmy/FDCT

cs.CV↗
arXiv2023

SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of pre-training data, particularly within the medical field. To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis. Our strategy harnesses the potential of multi-view information by incorporating two principal components. In the pre-training phase, we deploy a masked multi-view encoder devised to concurrently train masked multi-view observations through a range of diverse proxy tasks. These tasks span image reconstruction, rotation, contrastive learning, and a novel task that employs a mutual learning paradigm. This new task capitalizes on the consistency between predictions from various perspectives, enabling the extraction of hidden multi-view information from 3D medical data. In the fine-tuning stage, a cross-view decoder is developed to aggregate the multi-view information through a cross-attention block. Compared with the previous state-of-the-art self-supervised learning method Swin UNETR, SwinMM demonstrates a notable advantage on several medical image segmentation tasks. It allows for a smooth integration of multi-view information, significantly boosting both the accuracy and data-efficiency of the model. Code and models are available at https://github.com/UCSC-VLAA/SwinMM/.

cs.CV↗
arXiv2023

Two supercongruences involving truncated hypergeometric series

In this paper, we mainly establish two supercongruences involving truncated hypergeometric series by using some hypergeometric transformation formulas. The first supercongruence confirms a recent conjecture of the second author. The second supercongruence confirms a conjecture of Guo, Liu and Schlosser partially, and gives a parametric extension of a supercongruence of Long and Ramakrishna.

math.NT↗
arXiv2023

NeRF-Loc: Transformer-Based Object Localization Within Neural Radiance Fields

Neural Radiance Fields (NeRFs) have become a widely-applied scene representation technique in recent years, showing advantages for robot navigation and manipulation tasks. To further advance the utility of NeRFs for robotics, we propose a transformer-based framework, NeRF-Loc, to extract 3D bounding boxes of objects in NeRF scenes. NeRF-Loc takes a pre-trained NeRF model and camera view as input and produces labeled, oriented 3D bounding boxes of objects as output. Using current NeRF training tools, a robot can train a NeRF environment model in real-time and, using our algorithm, identify 3D bounding boxes of objects of interest within the NeRF for downstream navigation or manipulation tasks. Concretely, we design a pair of paralleled transformer encoder branches, namely the coarse stream and the fine stream, to encode both the context and details of target objects. The encoded features are then fused together with attention layers to alleviate ambiguities for accurate object localization. We have compared our method with conventional RGB(-D) based methods that take rendered RGB images and depths from NeRFs as inputs. Our method is better than the baselines.

cs.CV↗
arXiv2023

Energy-Efficient Routing Protocol Based on Multi-Threshold Segmentation in Wireless Sensors Networks for Precision Agriculture

Wireless sensor networks (WSNs), one of the fundamental technologies of the Internet of Things (IoT), can provide sensing and communication services efficiently for IoT-based applications, especially energy-limited applications. Clustering routing protocol plays an important role in reducing energy consumption and prolonging network lifetime. The cluster formation and cluster head selection are the key to improving the performance of the clustering routing protocol. An energy-efficient routing protocol based on multi-threshold segmentation (EERPMS) was proposed in this paper to improve the rationality of cluster formation and cluster head selection. In the stage of cluster formation, inspired by multi-threshold image segmentation, an innovative node clustering algorithm was developed. In the stage of cluster head selection, aiming at minimizing the network energy consumption, a calculation theory of the optimal number and location of cluster heads was established. Furthermore, a novel cluster head selection algorithm was constructed based on the residual energy and optimal location of cluster heads. Simulation results show that EERPMS can improve the distribution uniformity of cluster heads, prolong the network lifetime and save up to 64.50%, 58.60%, and 56.15% network energy as compared to RLEACH, CRPFCM, and FIGWO protocols respectively.

cs.NI↗
arXiv2023

Game Theory and Coverage Optimization Based Multihop Routing Protocol for Network Lifetime in Wireless Sensor Networks

Wireless sensor networks (WSNs) are self-organizing monitoring networks with a large number of randomly deployed microsensor nodes to collect various physical information to realize tasks such as intelligent perception, efficient control, and decision-making. However, WSN nodes are powered by batteries, so they will run out of energy after a certain time. This energy limitation will greatly constrain the network performance like network lifetime and energy efficiency. In this study, to prolong the network lifetime, we proposed a multi-hop routing protocol based on game theory and coverage optimization (MRP-GTCO). Briefly, in the stage of setup, two innovational strategies including a clustering game with penalty function and cluster head coverage set were designed to realize the uniformity of cluster head distribution and improve the rationality of cluster head election. In the data transmission stage, we first derived the applicable conditions theorem of inter-cluster multi-hop routing. Based on this, a novel multi-hop path selection algorithm related to residual energy and node degree was proposed to provide an energy-efficient data transmission path. The simulation results showed that the MRP-GTCO protocol can effectively reduce the network energy consumption and extend the network lifetime by 159.22%, 50.76%, and 16.46% compared with LGCA, RLEACH, and ECAGT protocols.

cs.NI↗
arXiv2023

Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation

Recommendation systems suffer in the strict cold-start (SCS) scenario, where the user-item interactions are entirely unavailable. The ID-based approaches completely fail to work. Cold-start recommenders, on the other hand, leverage item contents to map the new items to the existing ones. However, the existing SCS recommenders explore item contents in coarse-grained manners that introduce noise or information loss. Moreover, informative data sources other than item contents, such as users' purchase sequences and review texts, are ignored. We explore the role of the fine-grained item attributes in bridging the gaps between the existing and the SCS items and pre-train a knowledgeable item-attribute graph for SCS item recommendation. Our proposed framework, ColdGPT, models item-attribute correlations into an item-attribute graph by extracting fine-grained attributes from item contents. ColdGPT then transfers knowledge into the item-attribute graph from various available data sources, i.e., item contents, historical purchase sequences, and review texts of the existing items, via multi-task learning. To facilitate the positive transfer, ColdGPT designs submodules according to the natural forms of the data sources and coordinates the multiple pre-training tasks via unified alignment-and-uniformity losses. Our pre-trained item-attribute graph acts as an implicit, extendable item embedding matrix, which enables the SCS item embeddings to be easily acquired by inserting these items and propagating their attributes' embeddings. We carefully process three public datasets, i.e., Yelp, Amazon-home, and Amazon-sports, to guarantee the SCS setting for evaluation. Extensive experiments show that ColdGPT consistently outperforms the existing SCS recommenders by large margins and even surpasses models that are pre-trained on 75-224 times more, cross-domain data on two out of four datasets.

cs.IR↗
arXiv2023

Distance of PSR B0458+46 indicated by FAST HI absorption observations

The pulsar B0458+46 was previously believed to have a distance of about 1.3$~$kpc and to be associated with a nearby supernova remnant, SNR HB9 (G160.9+2.6). We observe the neutral hydrogen (HI) absorption spectrum of PSR B0458+46 by using the Five-hundred-meter Aperture Spherical radio Telescope (FAST), and detect two absorption lines at radial velocities of $V_{\rm LSR} = {-7.7}~{\rm km~s}^{-1}$ and $-28.1~{\rm km~s^{-1}}$. Based on the Galactic rotation curve with a modification factor correcting for the systematic stream in the anticenter region, we derive the kinematic distance of the farther absorption cloud, which is found to be located $2.7^{+0.9}_{-0.8}$ kpc away, just beyond the Perseus Arm. We also obtain a direct distance estimation of the absorption clouds, being $2.3_{-0.7}^{+1.1}$ kpc, based on a comparison of their velocity with the HI emission in the Perseus and Outer Arms that was well-defined by recently measured parallax tracers. As a result, we conclude that PSR B0458+46 should be located beyond the Perseus Arm, with a lower limit distance of 2.7 kpc, and therefore not associated with SNR HB9. The doubled distance indicates a deficiency of thermal electrons in the immediate outer Galaxy, with much less density than current models predict. Additionally, we detect a new high-velocity HI cloud in the direction of this pulsar.

astro-ph.HE↗
arXiv2023

Image Harmonization with Diffusion Model

Image composition in image editing involves merging a foreground image with a background image to create a composite. Inconsistent lighting conditions between the foreground and background often result in unrealistic composites. Image harmonization addresses this challenge by adjusting illumination and color to achieve visually appealing and consistent outputs. In this paper, we present a novel approach for image harmonization by leveraging diffusion models. We conduct a comparative analysis of two conditional diffusion models, namely Classifier-Guidance and Classifier-Free. Our focus is on addressing the challenge of adjusting illumination and color in foreground images to create visually appealing outputs that seamlessly blend with the background. Through this research, we establish a solid groundwork for future investigations in the realm of diffusion model-based image harmonization.

cs.CV↗
arXiv2023

Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits

Regret minimization in streaming multi-armed bandits (MABs) has been studied extensively in recent years. In the single-pass setting with $K$ arms and $T$ trials, a regret lower bound of $Ω(T^{2/3})$ has been proved for any algorithm with $o(K)$ memory (Maiti et al. [NeurIPS'21]; Agarwal at al. [COLT'22]). On the other hand, however, the previous best regret upper bound is still $O(K^{1/3} T^{2/3}\log^{1/3}(T))$, which is achieved by the streaming implementation of the simple uniform exploration. The $O(K^{1/3}\log^{1/3}(T))$ gap leaves the open question of the tight regret bound in the single-pass MABs with sublinear arm memory. In this paper, we answer this open problem and complete the picture of regret minimization in single-pass streaming MABs. We first improve the regret lower bound to $Ω(K^{1/3}T^{2/3})$ for algorithms with $o(K)$ memory, which matches the uniform exploration regret up to a logarithm factor in $T$. We then show that the $\log^{1/3}(T)$ factor is not necessary, and we can achieve $O(K^{1/3}T^{2/3})$ regret by finding an $\varepsilon$-best arm and committing to it in the rest of the trials. For regret minimization with high constant probability, we can apply the single-memory $\varepsilon$-best arm algorithms in Jin et al. [ICML'21] to obtain the optimal bound. Furthermore, for the expected regret minimization, we design an algorithm with a single-arm memory that achieves $O(K^{1/3} T^{2/3}\log(K))$ regret, and an algorithm with $O(\log^{*}(n))$-memory with the optimal $O(K^{1/3} T^{2/3})$ regret following the $\varepsilon$-best arm algorithm in Assadi and Wang [STOC'20]. We further tested the empirical performances of our algorithms. The simulation results show that the proposed algorithms consistently outperform the benchmark uniform exploration algorithm by a large margin, and on occasion, reduce the regret by up to 70%.

cs.LG↗
arXiv2023

Emergent quantum probability from full quantum dynamics and the role of energy conservation

We propose and study a toy model for the quantum measurements that yield the Born's rule of quantum probability. In this model, the electrons interact with local photon modes and the photon modes are dissipatively coupled with local photon reservoirs. We treat the interactions of the electrons and photons with full quantum mechanical description, while the dissipative dynamics of the photon modes are treated via the Lindblad master equation. By assigning double quantum dot setup for the electrons coupling with local photons and photonic reservoirs, we show that the Born's rule of quantum probability can emerge directly from microscopic quantum dynamics. We further discuss how the microscopic quantities such as the electron-photon couplings, detuning, and photon dissipation rate determine the quantum dynamics. Surprisingly, in the infinite long time measurement limit, the energy conservation already dictates the emergence of the Born's rule of quantum probability. For finite-time measurement, the local photon dissipation rate determines the characteristic time-scale for the completion of the measurement, while other microscopic quantities affect the measurement dynamics. Therefore, in genuine measurements, the measured probability is determined by both the local devices and the quantum mechanical wavefunction.

quant-ph↗
arXiv2023

Evaluating Stability in Massive Social Networks: Efficient Streaming Algorithms for Structural Balance

Structural balance theory studies stability in networks. Given a $n$-vertex complete graph $G=(V,E)$ whose edges are labeled positive or negative, the graph is considered \emph{balanced} if every triangle either consists of three positive edges (three mutual ``friends''), or one positive edge and two negative edges (two ``friends'' with a common ``enemy''). From a computational perspective, structural balance turns out to be a special case of correlation clustering with the number of clusters at most two. The two main algorithmic problems of interest are: $(i)$ detecting whether a given graph is balanced, or $(ii)$ finding a partition that approximates the \emph{frustration index}, i.e., the minimum number of edge flips that turn the graph balanced. We study these problems in the streaming model where edges are given one by one and focus on \emph{memory efficiency}. We provide randomized single-pass algorithms for: $(i)$ determining whether an input graph is balanced with $O(\log{n})$ memory, and $(ii)$ finding a partition that induces a $(1 + \varepsilon)$-approximation to the frustration index with $O(n \cdot \text{polylog}(n))$ memory. We further provide several new lower bounds, complementing different aspects of our algorithms such as the need for randomization or approximation. To obtain our main results, we develop a method using pseudorandom generators (PRGs) to sample edges between independently-chosen \emph{vertices} in graph streaming. Furthermore, our algorithm that approximates the frustration index improves the running time of the state-of-the-art correlation clustering with two clusters (Giotis-Guruswami algorithm [SODA 2006]) from $n^{O(1/\varepsilon^2)}$ to $O(n^2\log^3{n}/\varepsilon^2 + n\log n \cdot (1/\varepsilon)^{O(1/\varepsilon^4)})$ time for $(1+\varepsilon)$-approximation. These results may be of independent interest.

cs.DS↗
arXiv2023

Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System

There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become available in autonomous driving systems. How to empirically defend against these inaudible attacks remains an open question. Previous research investigates utilizing deep learning-based multimodal fusion for defense, without considering the model uncertainty in trustworthiness. As deep learning has been applied to increasingly sensitive tasks, uncertainty measurement is crucial in helping improve model robustness, especially in mission-critical scenarios. In this paper, we propose the Multimodal Fusion Framework (MFF) as an intelligent security system to defend against inaudible voice command attacks. MFF fuses heterogeneous audio-vision modalities using VGG family neural networks and achieves the detection accuracy of 92.25% in the comparative fusion method empirical study. Additionally, extensive experiments on audio-vision tasks reveal the model's uncertainty. Using Expected Calibration Errors, we measure calibration errors and Monte-Carlo Dropout to estimate the predictive distribution for the proposed models. Our findings show empirically to train robust multimodal models, improve standard accuracy and provide a further step toward interpretability. Finally, we discuss the pros and cons of our approach and its applicability for Advanced Driver Assistance Systems.

cs.CR↗