arXiv subjects

Chen Zhao

Publications and source records attributed to Chen Zhao.

At least 307 records · Page 17Linked to original sources

arXiv2023

xFBD: Focused Building Damage Dataset and Analysis

The xView2 competition and xBD dataset spurred significant advancements in overhead building damage detection, but the competition's pixel level scoring can lead to reduced solution performance in areas with tight clusters of buildings or uninformative context. We seek to advance automatic building damage assessment for disaster relief by proposing an auxiliary challenge to the original xView2 competition. This new challenge involves a new dataset and metrics indicating solution performance when damage is more local and limited than in xBD. Our challenge measures a network's ability to identify individual buildings and their damage level without excessive reliance on the buildings' surroundings. Methods that succeed on this challenge will provide more fine-grained, precise damage information than original xView2 solutions. The best-performing xView2 networks' performances dropped noticeably in our new limited/local damage detection task. The common causes of failure observed are that (1) building objects and their classifications are not separated well, and (2) when they are, the classification is strongly biased by surrounding buildings and other damage context. Thus, we release our augmented version of the dataset with additional object-level scoring metrics (https://drive.google.com/drive/folders/1VuQZuAg6-Yo8r5J4OCx3ZRpa_fv9aaDX?usp=sharing) to test independence and separability of building objects, alongside the pixel-level performance metrics of the original competition. We also experiment with new baseline models which improve independence and separability of building damage predictions. Our results indicate that building damage detection is not a fully-solved problem, and we invite others to use and build on our dataset augmentations and metrics.

cs.CV↗

arXiv2023

An Automated Vulnerability Detection Framework for Smart Contracts

With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology. Meanwhile, various vulnerabilities in smart contracts have been exploited by attackers to steal cryptocurrencies worth millions of dollars. The automatic detection of smart contract vulnerabilities therefore is an essential research problem. Existing solutions to this problem particularly rely on human experts to define features or different rules to detect vulnerabilities. However, this often causes many vulnerabilities to be ignored, and they are inefficient in detecting new vulnerabilities. In this study, to overcome such challenges, we propose a framework to automatically detect vulnerabilities in smart contracts on the blockchain. More specifically, first, we utilize novel feature vector generation techniques from bytecode of smart contract since the source code of smart contracts are rarely available in public. Next, the collected vectors are fed into our novel metric learning-based deep neural network(DNN) to get the detection result. We conduct comprehensive experiments on large-scale benchmarks, and the quantitative results demonstrate the effectiveness and efficiency of our approach.

cs.CR↗

arXiv2023

AGMN: Association Graph-based Graph Matching Network for Coronary Artery Semantic Labeling on Invasive Coronary Angiograms

Semantic labeling of coronary arterial segments in invasive coronary angiography (ICA) is important for automated assessment and report generation of coronary artery stenosis in the computer-aided diagnosis of coronary artery disease (CAD). Inspired by the training procedure of interventional cardiologists for interpreting the structure of coronary arteries, we propose an association graph-based graph matching network (AGMN) for coronary arterial semantic labeling. We first extract the vascular tree from invasive coronary angiography (ICA) and convert it into multiple individual graphs. Then, an association graph is constructed from two individual graphs where each vertex represents the relationship between two arterial segments. Using the association graph, the AGMN extracts the vertex features by the embedding module, aggregates the features from adjacent vertices and edges by graph convolution network, and decodes the features to generate the semantic mappings between arteries. By learning the mapping of arterial branches between two individual graphs, the unlabeled arterial segments are classified by the labeled segments to achieve semantic labeling. A dataset containing 263 ICAs was employed to train and validate the proposed model, and a five-fold cross-validation scheme was performed. Our AGMN model achieved an average accuracy of 0.8264, an average precision of 0.8276, an average recall of 0.8264, and an average F1-score of 0.8262, which significantly outperformed existing coronary artery semantic labeling methods. In conclusion, we have developed and validated a new algorithm with high accuracy, interpretability, and robustness for coronary artery semantic labeling on ICAs.

cs.CV↗

arXiv2022

Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images

Background. Functional assessment of right ventricle (RV) using gated myocardial perfusion single-photon emission computed tomography (MPS) heavily relies on the precise extraction of right ventricular contours. In this paper, we present a new deep-learning-based model integrating both the spatial and temporal features in gated MPS images to perform the segmentation of the RV epicardium and endocardium. Methods. By integrating the spatial features from each cardiac frame of the gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we developed a Spatial-Temporal V-Net (ST-VNet) for automatic extraction of RV endocardial and epicardial contours. In the ST-VNet, a V-Net is employed to hierarchically extract spatial features, and convolutional long-term short-term memory (ConvLSTM) units are added to the skip-connection pathway to extract the temporal features. The input of the ST-VNet is ECG-gated sequential frames of the MPS images and the output is the probability map of the epicardial or endocardial masks. A Dice similarity coefficient (DSC) loss which penalizes the discrepancy between the model prediction and the ground truth was adopted to optimize the segmentation model. Results. Our segmentation model was trained and validated on a retrospective dataset with 45 subjects, and the cardiac cycle of each subject was divided into 8 gates. The proposed ST-VNet achieved a DSC of 0.8914 and 0.8157 for the RV epicardium and endocardium segmentation, respectively. The mean absolute error, the mean squared error, and the Pearson correlation coefficient of the RV ejection fraction (RVEF) between the ground truth and the model prediction were 0.0609, 0.0830, and 0.6985. Conclusion. Our proposed ST-VNet is an effective model for RV segmentation. It has great promise for clinical use in RV functional assessment.

eess.IV↗

arXiv2022

Barren plateaus from learning scramblers with local cost functions

The existence of barren plateaus has recently revealed new training challenges in quantum machine learning (QML). Uncovering the mechanisms behind barren plateaus is essential in understanding the scope of problems that QML can efficiently tackle. Barren plateaus have recently been shown to exist when learning global properties of random unitaries, which is relevant when learning black hole dynamics. Establishing whether local cost functions can circumvent these barren plateaus is pertinent if we hope to apply QML to quantum many-body systems. We prove a no-go theorem showing that local cost functions encounter barren plateaus in learning random unitary properties.

quant-ph↗

arXiv2022

ETAD: Training Action Detection End to End on a Laptop

Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further alleviate the computational redundancy in training, we propose to dynamically sample only a small subset of proposals during training. Moreover, various sampling strategies and ratios are studied for both the encoder and detector. ETAD achieves state-of-the-art performance on TAD benchmarks with remarkable efficiency. On ActivityNet-1.3, training ETAD in 18 hours can reach 38.25% average mAP with only 1.3 GB memory consumption per video under end-to-end training. Our code will be publicly released.

cs.CV↗

arXiv2022

A New Hip Fracture Risk Index Derived from FEA-Computed Proximal Femur Fracture Loads and Energies-to-Failure

Hip fracture risk assessment is an important but challenging task. Quantitative CT-based patient specific finite element analysis (FEA) computes the force (fracture load) to break the proximal femur in a particular loading condition. It provides different structural information about the proximal femur that can influence a subject overall fracture risk. To obtain a more robust measure of fracture risk, we used principal component analysis (PCA) to develop a global FEA computed fracture risk index that incorporates the FEA-computed yield and ultimate failure loads and energies to failure in four loading conditions (single-limb stance and impact from a fall onto the posterior, posterolateral, and lateral aspects of the greater trochanter) of 110 hip fracture subjects and 235 age and sex matched control subjects from the AGES-Reykjavik study. We found that the first PC (PC1) of the FE parameters was the only significant predictor of hip fracture. Using a logistic regression model, we determined if prediction performance for hip fracture using PC1 differed from that using FE parameters combined by stratified random resampling with respect to hip fracture status. The results showed that the average of the area under the receive operating characteristic curve (AUC) using PC1 was always higher than that using all FE parameters combined in the male subjects. The AUC of PC1 and AUC of the FE parameters combined were not significantly different than that in the female subjects or in all subjects

cs.LG↗

arXiv2022

Estimating more camera poses for ego-centric videos is essential for VQ3D

Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark. Given an egocentric video, the goal is to answer queries of the form "Where did I last see object X?", where the query object X is specified as a static image, and the answer should be a 3D displacement vector pointing to object X. However, current techniques use naive ways to estimate the camera poses of video frames, resulting in a low query with pose (QwP) ratio, thus a poor overall success rate. We design a new pipeline for the challenging egocentric video camera pose estimation problem in our work. Moreover, we revisit the current VQ3D framework and optimize it in terms of performance and efficiency. As a result, we get the top-1 overall success rate of 25.8% on VQ3D leaderboard, which is two times better than the 8.7% reported by the baseline.

cs.CV↗

arXiv2022

A high-frequency mobility big-data reveals how COVID-19 spread across professions, locations and age groups

As infected and vaccinated population increases, some countries decided not to impose non-pharmaceutical intervention measures anymore and to coexist with COVID-19. However, we do not have a comprehensive understanding of its consequence , especially for China where most population has not been infected and most Omicron transmissions are silent. This paper serves as the first study to reveal the complete silent transmission dynamics of COVID-19 overlaying a big data of more than 0.7 million real individual mobility tracks without any intervention measures throughout a week in a Chinese city, with an extent of completeness and realism not attained in existing studies. Together with the empirically inferred transmission rate of COVID-19, we find surprisingly that with only 70 citizens to be infected initially, 0.33 million becomes infected silently at last. We also reveal a characteristic daily periodic pattern of the transmission dynamics, with peaks in mornings and afternoons. In addition, retailing, catering and hotel staff are more likely to get infected than other professions. Unlike all other age groups and professions, elderly and retirees are more likely to get infected at home than outside home.

physics.soc-ph↗

arXiv2022

OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos

Egocentric videos capture sequences of human activities from a first-person perspective and can provide rich multimodal signals. However, most current localization methods use third-person videos and only incorporate visual information. In this work, we take a deep look into the effectiveness of audiovisual context in detecting actions in egocentric videos and introduce a simple-yet-effective approach via Observing, Watching, and Listening (OWL). OWL leverages audiovisual information and context for egocentric temporal action localization (TAL). We validate our approach in two large-scale datasets, EPIC-Kitchens, and HOMAGE. Extensive experiments demonstrate the relevance of the audiovisual temporal context. Namely, we boost the localization performance (mAP) over visual-only models by +2.23% and +3.35% in the above datasets.

cs.CV↗

arXiv2022

Re-Examining Calibration: The Case of Question Answering

For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions. Focusing on the practical application of open-domain question answering, we examine conventional calibration methods applied on the widely-used retriever-reader pipeline, all of which do not bring significant gains under our new MacroCE metric. Toward better calibration, we propose a new calibration method (ConsCal) that uses not just final model predictions but whether multiple model checkpoints make consistent predictions. Altogether, we provide an alternative view of calibration along with a new metric, re-evaluation of existing calibration methods on our metric, and proposal of a more effective calibration method.

cs.CL↗

arXiv2022

$L^2$ representation of Simpson-Mochizuki's prolongation of Higgs bundles and the Kawamata-Viehweg vanishing theorem for semistable parabolic Higgs bundles

In this paper, we provide an $L^2$ fine resolution of the prolongation of a nilpotent harmonic bundle in the sense of Simpson-Mochizuki (an analytic analogue of the Kashiwara-Malgrange filtrations). This is the logarithmic analogue of Cattani-Kaplan-Schmid's and Kashiwara-Kawai's results on the $L^2$ interpretation of the intersection complex. As an application, we give an $L^2$-theoretic proof to the Nadel-Kawamata-Viehweg vanishing theorem with coefficients in a nilpotent Higgs bundle.

math.AG↗

arXiv2022

Kollár's Package for Twisted Saito's S-sheaves

We generalize Kollár's conjecture (including torsion freeness, injectivity theorem, vanishing theorem and decomposition theorem) to Saito's $S$-sheaves twisted by a $\mathbb{Q}$-divisor. This gives a uniform treatment for various kinds of Kollár's package in different topics in complex geometry. As a consequence we prove Kollár's package of pluricanonical bundles twisted by a certain multiplier ideal sheaf. The method of the present paper is $L^2$-theoretic.

math.AG↗

arXiv2022

SoccerNet 2022 Challenges Results

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.

cs.CV↗

arXiv2022

DCE: Offline Reinforcement Learning With Double Conservative Estimates

Offline Reinforcement Learning has attracted much interest in solving the application challenge for traditional reinforcement learning. Offline reinforcement learning uses previously-collected datasets to train agents without any interaction. For addressing the overestimation of OOD (out-of-distribution) actions, conservative estimates give a low value for all inputs. Previous conservative estimation methods are usually difficult to avoid the impact of OOD actions on Q-value estimates. In addition, these algorithms usually need to lose some computational efficiency to achieve the purpose of conservative estimation. In this paper, we propose a simple conservative estimation method, double conservative estimates (DCE), which use two conservative estimation method to constraint policy. Our algorithm introduces V-function to avoid the error of in-distribution action while implicit achieving conservative estimation. In addition, our algorithm uses a controllable penalty term changing the degree of conservatism in training. We theoretically show how this method influences the estimation of OOD actions and in-distribution actions. Our experiment separately shows that two conservative estimation methods impact the estimation of all state-action. DCE demonstrates the state-of-the-art performance on D4RL.

cs.LG↗

arXiv2022

Automatic reorientation by deep learning to generate short axis SPECT myocardial perfusion images

Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. Methods: A total of 254 patients were enrolled, including 228 stress SPECT MPIs and 248 rest SPECT MPIs. Five-fold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced operator and used as the ground truth. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: 1) optimize the translation parameters while fixing the rotation parameters; 2) optimize rotation parameters while fixing the translation parameters; 3) optimize both translation and rotation parameters together.

eess.IV↗

arXiv2022

End-to-End Active Speaker Detection

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and contextual predictions are jointly learned. Our end-to-end trainable network simultaneously learns multi-modal embeddings and aggregates spatio-temporal context. This results in more suitable feature representations and improved performance in the ASD task. We also introduce interleaved graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance. Finally, we design a weakly-supervised strategy, which demonstrates that the ASD problem can also be approached by utilizing audiovisual data but relying exclusively on audio annotations. We achieve this by modelling the direct relationship between the audio signal and the possible sound sources (speakers), as well as introducing a contrastive loss. All the resources of this project will be made available at: https://github.com/fuankarion/end-to-end-asd.

cs.CV↗

arXiv2022

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. This task contrasts with the one considered by most existing deep learning methods which typically assume that the testing objects have been observed during training. To handle the unseen objects, we follow a retrieval-based strategy and prevent the network from learning object-specific features by computing multi-scale local similarities between the query image and synthetically-generated reference images. We then introduce an adaptive fusion module that robustly aggregates the local similarities into a global similarity score of pairwise images. Furthermore, we speed up the retrieval process by developing a fast retrieval strategy. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works. Our code and pre-trained models are available at https://sailor-z.github.io/projects/Unseen_Object_Pose.html.

cs.CV↗