arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,045 records · Page 58Linked to original sources

arXiv2023

Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation

Medical image segmentation is a fundamental task in the community of medical image analysis. In this paper, a novel network architecture, referred to as Convolution, Transformer, and Operator (CTO), is proposed. CTO employs a combination of Convolutional Neural Networks (CNNs), Vision Transformer (ViT), and an explicit boundary detection operator to achieve high recognition accuracy while maintaining an optimal balance between accuracy and efficiency. The proposed CTO follows the standard encoder-decoder segmentation paradigm, where the encoder network incorporates a popular CNN backbone for capturing local semantic information, and a lightweight ViT assistant for integrating long-range dependencies. To enhance the learning capacity on boundary, a boundary-guided decoder network is proposed that uses a boundary mask obtained from a dedicated boundary detection operator as explicit supervision to guide the decoding learning process. The performance of the proposed method is evaluated on six challenging medical image segmentation datasets, demonstrating that CTO achieves state-of-the-art accuracy with a competitive model complexity.

cs.CV↗

arXiv2023

Limiting distributions of graph-based test statistics on sparse and dense graphs

Two-sample tests utilizing a similarity graph on observations are useful for high-dimensional and non-Euclidean data due to their flexibility and good performance under a wide range of alternatives. Existing works mainly focused on sparse graphs, such as graphs with the number of edges in the order of the number of observations, and their asymptotic results imposed strong conditions on the graph that can easily be violated by commonly constructed graphs they suggested. Moreover, the graph-based tests have better performance with denser graphs under many settings. In this work, we establish the theoretical ground for graph-based tests with graphs ranging from those recommended in current literature to much denser ones.

math.ST↗

arXiv2023

Validity of black hole complementarity in the context of generalized uncertainty principle

Recently, Elias C. Vagenas et al and Yongwan Gim et al studied the validity of the no-cloning theorem in the context of generalized uncertainty principle (GUP), but they came to conflicting conclusions. With this in mind, we investigate the corrections to the temperature for Schwarzschild black hole in the context of different forms of GUP, and obtain the required energy to duplicate information for the Schwarzschild black hole, it shows that the required energy is greater than the mass of black hole, i.e. the no-cloning theorem in the present of GUP is safe.

gr-qc↗

arXiv2023

The Second Monocular Depth Estimation Challenge

This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC). This edition was open to methods using any form of supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge was based around the SYNS-Patches dataset, which features a wide diversity of environments with high-quality dense ground-truth. This includes complex natural environments, e.g. forests or fields, which are greatly underrepresented in current benchmarks. The challenge received eight unique submissions that outperformed the provided SotA baseline on any of the pointcloud- or image-based metrics. The top supervised submission improved relative F-Score by 27.62%, while the top self-supervised improved it by 16.61%. Supervised submissions generally leveraged large collections of datasets to improve data diversity. Self-supervised submissions instead updated the network architecture and pretrained backbones. These results represent a significant progress in the field, while highlighting avenues for future research, such as reducing interpolation artifacts at depth boundaries, improving self-supervised indoor performance and overall natural image accuracy.

cs.CV↗

arXiv2023

Elucidating the active phases of CoOx films on Au(111) in the CO Oxidation Reaction

Using CoOx thin films supported on Au(111) single crystal surfaces as model catalysts for the CO oxidation reaction we show that three reaction regimes exist in response to chemical and topographic restructuring of the CoOx catalyst as a function of reactant gas phase CO/O2 stoichiometry a finding that highlights the versatility of catalysts and their evolution in response to reaction conditions. Under oxygen-lean conditions and moderate temperatures (below 150C degrees) partially oxidized films containing CoO were found to be efficient catalysts. In contrast, stoichiometric CoO films containing only Co2+ form carbonates in the presence of CO that poison the reaction below 300 C degrees. Under oxygen-rich conditions a more oxidized catalyst phase forms containing Co3+ species that is effective in a wide temperature range. Resonant photoemission spectroscopy (ResPES) revealed the unique role of Co3+ sites in catalyzing the CO oxidation. DFT calculations provided deeper insights into the pathway and free energy barriers for the reactions on these oxide phases.

cond-mat.mtrl-sci↗

arXiv2023

CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection

The combination of LiDAR and camera modalities is proven to be necessary and typical for 3D object detection according to recent studies. Existing fusion strategies tend to overly rely on the LiDAR modal in essence, which exploits the abundant semantics from the camera sensor insufficiently. However, existing methods cannot rely on information from other modalities because the corruption of LiDAR features results in a large domain gap. Following this, we propose CrossFusion, a more robust and noise-resistant scheme that makes full use of the camera and LiDAR features with the designed cross-modal complementation strategy. Extensive experiments we conducted show that our method not only outperforms the state-of-the-art methods under the setting without introducing an extra depth estimation network but also demonstrates our model's noise resistance without re-training for the specific malfunction scenarios by increasing 5.2\% mAP and 2.4\% NDS.

cs.CV↗

arXiv2023

Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation

As growing usage of social media websites in the recent decades, the amount of news articles spreading online rapidly, resulting in an unprecedented scale of potentially fraudulent information. Although a plenty of studies have applied the supervised machine learning approaches to detect such content, the lack of gold standard training data has hindered the development. Analysing the single data format, either fake text description or fake image, is the mainstream direction for the current research. However, the misinformation in real-world scenario is commonly formed as a text-image pair where the news article/news title is described as text content, and usually followed by the related image. Given the strong ability of learning features without labelled data, contrastive learning, as a self-learning approach, has emerged and achieved success on the computer vision. In this paper, our goal is to explore the constrastive learning in the domain of misinformation identification. We developed a self-learning model and carried out the comprehensive experiments on a public data set named COSMOS. Comparing to the baseline classifier, our model shows the superior performance of non-matched image-text pair detection (approximately 10%) when the training data is insufficient. In addition, we observed the stability for contrsative learning and suggested the use of it offers large reductions in the number of training data, whilst maintaining comparable classification results.

cs.LG↗

arXiv2023

Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes

Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to corrupted estimations. Many multi-frame methods handle dynamic areas by identifying them with explicit masks and compensating the multi-view cues with monocular cues represented as local monocular depth or features. The improvements are limited due to the uncontrolled quality of the masks and the underutilized benefits of the fusion of the two types of cues. In this paper, we propose a novel method to learn to fuse the multi-view and monocular cues encoded as volumes without needing the heuristically crafted masks. As unveiled in our analyses, the multi-view cues capture more accurate geometric information in static areas, and the monocular cues capture more useful contexts in dynamic areas. To let the geometric perception learned from multi-view cues in static areas propagate to the monocular representation in dynamic areas and let monocular cues enhance the representation of multi-view cost volume, we propose a cross-cue fusion (CCF) module, which includes the cross-cue attention (CCA) to encode the spatially non-local relative intra-relations from each source to enhance the representation of the other. Experiments on real-world datasets prove the significant effectiveness and generalization ability of the proposed method.

cs.CV↗

arXiv2023

High dynamic range open-loop current measurement based on diamond quantum magnetometer achieving ppm scale precision

Negatively charged nitrogen-vacancy (NV) centers in diamond have been extensively studied as a promising high sensitivity solid-state magnetic field sensor at room temperature. However, their use for current sensing applications is limited due to the challenge of integration and miniaturization of the diamond NV sensor. Here, we demonstrate an integrated NV sensor fabricated with standard microfabrication process. The sensor device incorporated with a toroidal magnetic yoke enables a high-precision wide range direct current sensing with galvanic isolation. The performance of the diamond NV current sensor in an open loop configuration has been investigated. A current measuring range of 0 A ~ 1000 A with an uncertainty of 46 ppm are achieved. Taking advantage of dual spin resonance modulation, temperature drift is suppressed to 10 ppm/K. This configuration opens new possibilities as a robust and scalable platform for current quantum sensing technologies.

physics.ins-det↗

arXiv2023

A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition

Recent advances in event-based research prioritize sparsity and temporal precision. Approaches using dense frame-based representations processed via well-pretrained CNNs are being replaced by the use of sparse point-based representations learned through graph CNNs (GCN). Yet, the efficacy of these graph methods is far behind their frame-based counterparts with two limitations. ($i$) Biased graph construction without carefully integrating variant attributes ($i.e.$, semantics, spatial and temporal cues) for each vertex, leading to imprecise graph representation. ($ii$) Deficient learning because of the lack of well-pretrained models available. Here we solve the first problem by proposing a new event-based GCN (EDGCN), with a dynamic aggregation module to integrate all attributes of vertices adaptively. To address the second problem, we introduce a novel learning framework called cross-representation distillation (CRD), which leverages the dense representation of events as a cross-representation auxiliary to provide additional supervision and prior knowledge for the event graph. This frame-to-graph distillation allows us to benefit from the large-scale priors provided by CNNs while still retaining the advantages of graph-based models. Extensive experiments show our model and learning framework are effective and generalize well across multiple vision tasks.

cs.CV↗

arXiv2023

Image Quality-aware Diagnosis via Meta-knowledge Co-embedding

Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing low-quality images while ignoring their potential value for models. Through effectively learning and leveraging the knowledge of degradations, models can better resist their adverse effects and avoid misdiagnosis. In this paper, we raise the problem of image quality-aware diagnosis, which aims to take advantage of low-quality images and image quality labels to achieve a more accurate and robust diagnosis. However, the diversity of degradations and superficially unrelated targets between image quality assessment and disease diagnosis makes it still quite challenging to effectively leverage quality labels to assist diagnosis. Thus, to tackle these issues, we propose a novel meta-knowledge co-embedding network, consisting of two subnets: Task Net and Meta Learner. Task Net constructs an explicit quality information utilization mechanism to enhance diagnosis via knowledge co-embedding features, while Meta Learner ensures the effectiveness and constrains the semantics of these features via meta-learning and joint-encoding masking. Superior performance on five datasets with four widely-used medical imaging modalities demonstrates the effectiveness and generalizability of our method.

eess.IV↗

arXiv2023

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

A backdoor attack allows a malicious user to manipulate the environment or corrupt the training data, thus inserting a backdoor into the trained agent. Such attacks compromise the RL system's reliability, leading to potentially catastrophic results in various key fields. In contrast, relatively limited research has investigated effective defenses against backdoor attacks in RL. This paper proposes the Recovery Triggered States (RTS) method, a novel approach that effectively protects the victim agents from backdoor attacks. RTS involves building a surrogate network to approximate the dynamics model. Developers can then recover the environment from the triggered state to a clean state, thereby preventing attackers from activating backdoors hidden in the agent by presenting the trigger. When training the surrogate to predict states, we incorporate agent action information to reduce the discrepancy between the actions taken by the agent on predicted states and the actions taken on real states. RTS is the first approach to defend against backdoor attacks in a single-agent setting. Our results show that using RTS, the cumulative reward only decreased by 1.41% under the backdoor attack.

cs.LG↗

arXiv2023

A property on monochromatic copies of graphs containing a triangle

A graph $H$ is called common and respectively, strongly common if the number of monochromatic copies of $H$ in a 2-edge-coloring $ϕ$ of a large clique is asymptotically minimised by the random coloring with an equal proportion of each color and respectively, by the random coloring with the same proportion of each color as in $ϕ$. A well-known theorem of Jagger, {\v S}t'ov{\' i}{\v c}ek and Thomason states that every graph containing a $K_4$ is not common. Here we prove an analogous result that every graph containing a $K_3$ and with at least four edges is not strongly common.

math.CO↗

arXiv2023

Improving ABR Performance for Short Video Streaming Using Multi-Agent Reinforcement Learning with Expert Guidance

In the realm of short video streaming, popular adaptive bitrate (ABR) algorithms developed for classical long video applications suffer from catastrophic failures because they are tuned to solely adapt bitrates. Instead, short video adaptive bitrate (SABR) algorithms have to properly determine which video at which bitrate level together for content prefetching, without sacrificing the users' quality of experience (QoE) and yielding noticeable bandwidth wastage jointly. Unfortunately, existing SABR methods are inevitably entangled with slow convergence and poor generalization. Thus, in this paper, we propose Incendio, a novel SABR framework that applies Multi-Agent Reinforcement Learning (MARL) with Expert Guidance to separate the decision of video ID and video bitrate in respective buffer management and bitrate adaptation agents to maximize the system-level utilized score modeled as a compound function of QoE and bandwidth wastage metrics. To train Incendio, it is first initialized by imitating the hand-crafted expert rules and then fine-tuned through the use of MARL. Results from extensive experiments indicate that Incendio outperforms the current state-of-the-art SABR algorithm with a 53.2% improvement measured by the utility score while maintaining low training complexity and inference time.

cs.MM↗

arXiv2023

Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth

Existing monocular depth estimation methods have achieved excellent robustness in diverse scenes, but they can only retrieve affine-invariant depth, up to an unknown scale and shift. However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency. To solve this problem, we propose a locally weighted linear regression method to recover the scale and shift with very sparse anchor points, which ensures the scale consistency along consecutive frames. Extensive experiments show that our method can boost the performance of existing state-of-the-art approaches by 50% at most over several zero-shot benchmarks. Besides, we merge over 6.3 million RGBD images to train strong and robust depth models. Our produced ResNet50-backbone model even outperforms the state-of-the-art DPT ViT-Large model. Combining with geometry-based reconstruction methods, we formulate a new dense 3D scene reconstruction pipeline, which benefits from both the scale consistency of sparse points and the robustness of monocular methods. By performing the simple per-frame prediction over a video, the accurate 3D scene shape can be recovered.

cs.CV↗

arXiv2023

DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images

Computer-assisted automatic analysis of diabetic retinopathy (DR) is of great importance in reducing the risks of vision loss and even blindness. Ultra-wide optical coherence tomography angiography (UW-OCTA) is a non-invasive and safe imaging modality in DR diagnosis system, but there is a lack of publicly available benchmarks for model development and evaluation. To promote further research and scientific benchmarking for diabetic retinopathy analysis using UW-OCTA images, we organized a challenge named "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022). The challenge consists of three tasks: segmentation of DR lesions, image quality assessment and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams from geographically diverse institutes submitting different solutions in these three tasks, respectively. This paper presents a summary and analysis of the top-performing solutions and results for each task of the challenge. The obtained results from top algorithms indicate the importance of data augmentation, model architecture and ensemble of networks in improving the performance of deep learning models. These findings have the potential to enable new developments in diabetic retinopathy analysis. The challenge remains open for post-challenge registrations and submissions for benchmarking future methodology developments.

eess.IV↗

arXiv2023

HNeRV: A Hybrid Neural Representation for Videos

Implicit neural representations store videos as neural networks and have performed well for various vision tasks such as video compression and denoising. With frame index or positional index as input, implicit representations (NeRV, E-NeRV, \etc) reconstruct video from fixed and content-agnostic embeddings. Such embedding largely limits the regression capacity and internal generalization for video interpolation. In this paper, we propose a Hybrid Neural Representation for Videos (HNeRV), where a learnable encoder generates content-adaptive embeddings, which act as the decoder input. Besides the input embedding, we introduce HNeRV blocks, which ensure model parameters are evenly distributed across the entire network, such that higher layers (layers near the output) can have more capacity to store high-resolution content and video details. With content-adaptive embeddings and re-designed architecture, HNeRV outperforms implicit methods in video regression tasks for both reconstruction quality ($+4.7$ PSNR) and convergence speed ($16\times$ faster), and shows better internal generalization. As a simple and efficient video representation, HNeRV also shows decoding advantages for speed, flexibility, and deployment, compared to traditional codecs~(H.264, H.265) and learning-based compression methods. Finally, we explore the effectiveness of HNeRV on downstream tasks such as video compression and video inpainting. We provide project page at https://haochen-rye.github.io/HNeRV, and Code at https://github.com/haochen-rye/HNeRV

cs.CV↗

arXiv2023

FRA-LSTM: A Vessel Trajectory Prediction Method Based on Fusion of the Forward and Reverse Sub-Network

In order to improve the vessel's capacity and ensure maritime traffic safety, vessel intelligent trajectory prediction plays an essential role in the vessel's smart navigation and intelligent collision avoidance system. However, current researchers only focus on short-term or long-term vessel trajectory prediction, which leads to insufficient accuracy of trajectory prediction and lack of in-depth mining of comprehensive historical trajectory data. This paper proposes an Automatic Identification System (AIS) data-driven long short-term memory (LSTM) method based on the fusion of the forward sub-network and the reverse sub-network (termed as FRA-LSTM) to predict the vessel trajectory. The forward sub-network in our method combines LSTM and attention mechanism to mine features of forward historical trajectory data. Simultaneously, the reverse sub-network combines bi-directional LSTM (BiLSTM) and attention mechanism to mine features of backward historical trajectory data. Finally, the final predicted trajectory is generated by fusing output features of the forward and reverse sub-network. Based on plenty of experiments, we prove that the accuracy of our proposed method in predicting short-term and mid-term trajectories has increased by 96.8% and 86.5% on average compared with the BiLSTM and Seq2seq. Furthermore, the average accuracy of our method is 90.1% higher than that of compared the BiLSTM and Seq2seq in predicting long-term trajectories.

cs.CY↗