Searcharxiv⌕ Search

arXiv subjects

Xin Yang

Publications and source records attributed to Xin Yang.

At least 271 records · Page 15Linked to original sources
arXiv2023

Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions

Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg). However, the diverse implementation strategies of various models have led to an extremely complex MedISeg system, resulting in a potential problem of unfair result comparisons. In this paper, we collect a series of MedISeg tricks for different model implementation phases (i.e., pre-training model, data pre-processing, data augmentation, model implementation, model inference, and result post-processing), and experimentally explore the effectiveness of these tricks on consistent baselines. With the extensive experimental results on both the representative 2D and 3D medical image datasets, we explicitly clarify the effect of these tricks. Moreover, based on the surveyed tricks, we also open-sourced a strong MedISeg repository, where each component has the advantage of plug-and-play. We believe that this milestone work not only completes a comprehensive and complementary survey of the state-of-the-art MedISeg approaches, but also offers a practical guide for addressing the future medical image processing challenges including but not limited to small dataset, class imbalance learning, multi-modality learning, and domain adaptation. The code and training weights have been released at: https://github.com/hust-linyi/seg_trick.

cs.CV↗
arXiv2023

Hierarchical Agent-based Reinforcement Learning Framework for Automated Quality Assessment of Fetal Ultrasound Video

Ultrasound is the primary modality to examine fetal growth during pregnancy, while the image quality could be affected by various factors. Quality assessment is essential for controlling the quality of ultrasound images to guarantee both the perceptual and diagnostic values. Existing automated approaches often require heavy structural annotations and the predictions may not necessarily be consistent with the assessment results by human experts. Furthermore, the overall quality of a scan and the correlation between the quality of frames should not be overlooked. In this work, we propose a reinforcement learning framework powered by two hierarchical agents that collaboratively learn to perform both frame-level and video-level quality assessments. It is equipped with a specially-designed reward mechanism that considers temporal dependency among frame quality and only requires sparse binary annotations to train. Experimental results on a challenging fetal brain dataset verify that the proposed framework could perform dual-level quality assessment and its predictions correlate well with the subjective assessment results.

eess.IV↗
arXiv2023

Label Inference Attack against Split Learning under Regression Setting

As a crucial building block in vertical Federated Learning (vFL), Split Learning (SL) has demonstrated its practice in the two-party model training collaboration, where one party holds the features of data samples and another party holds the corresponding labels. Such method is claimed to be private considering the shared information is only the embedding vectors and gradients instead of private raw data and labels. However, some recent works have shown that the private labels could be leaked by the gradients. These existing attack only works under the classification setting where the private labels are discrete. In this work, we step further to study the leakage in the scenario of the regression model, where the private labels are continuous numbers (instead of discrete labels in classification). This makes previous attacks harder to infer the continuous labels due to the unbounded output range. To address the limitation, we propose a novel learning-based attack that integrates gradient information and extra learning regularization objectives in aspects of model training properties, which can infer the labels under regression settings effectively. The comprehensive experiments on various datasets and models have demonstrated the effectiveness of our proposed attack. We hope our work can pave the way for future analyses that make the vFL framework more secure.

cs.CR↗
arXiv2023

Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds

Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods either suffer from structure distortion due to ignorance of rigid motion consistency or require explicit pose estimation and 3D object segmentation. Errors of estimated poses and segmented objects would yield inaccurate rigidity constraints and in turn mislead scene flow estimation. In this paper, we propose a novel weight-sharing aggregation (WSA) method for feature and scene flow up-sampling. WSA does not rely on estimated poses and segmented objects, and can implicitly enforce rigidity constraints to avoid structure distortion in scene flow estimation. To further exploit geometric information and preserve local structure, we design a deformation degree module aim to keep the local region invariance. We modify the PointPWC-Net and integrate the proposed WSA and deformation degree module into the enhanced PointPWC-Net to derive an end-to-end scene flow estimation network, called WSAFlowNet. Extensive experimental results on the FlyingThings3D and KITTI datasets demonstrate that our WSAFlowNet achieves the state-of-the-art performance and outperforms previous methods by a large margin. We will release the source code at https://github.com/wangyunlhr/WSAFlowNet.git.

cs.CV↗
arXiv2023

Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images

Medical anomaly detection is a crucial yet challenging task aimed at recognizing abnormal images to assist in diagnosis. Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples deviating from the normal profile as anomalies in the testing phase. Many readily available unlabeled images containing anomalies are thus ignored in the training phase, restricting the performance. To solve this problem, we introduce one-class semi-supervised learning (OC-SSL) to utilize known normal and unlabeled images for training, and propose Dual-distribution Discrepancy for Anomaly Detection (DDAD) based on this setting. Ensembles of reconstruction networks are designed to model the distribution of normal images and the distribution of both normal and unlabeled images, deriving the normative distribution module (NDM) and unknown distribution module (UDM). Subsequently, the intra-discrepancy of NDM and inter-discrepancy between the two modules are designed as anomaly scores. Furthermore, we propose a new perspective on self-supervised learning, which is designed to refine the anomaly scores rather than detect anomalies directly. Five medical datasets, including chest X-rays, brain MRIs and retinal fundus images, are organized as benchmarks for evaluation. Experiments on these benchmarks comprehensively compare a wide range of anomaly detection methods and demonstrate that our method achieves significant gains and outperforms the state-of-the-art. Code and organized benchmarks are available at https://github.com/caiyu6666/DDAD-ASR.

cs.CV↗
arXiv2023

Iterative Geometry Encoding Volume for Stereo Matching

Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this paper, we propose Iterative Geometry Encoding Volume (IGEV-Stereo), a new deep network architecture for stereo matching. The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map. To speed up the convergence, we exploit GEV to regress an accurate starting point for ConvGRUs iterations. Our IGEV-Stereo ranks $1^{st}$ on KITTI 2015 and 2012 (Reflective) among all published methods and is the fastest among the top 10 methods. In addition, IGEV-Stereo has strong cross-dataset generalization as well as high inference efficiency. We also extend our IGEV to multi-view stereo (MVS), i.e. IGEV-MVS, which achieves competitive accuracy on DTU benchmark. Code is available at https://github.com/gangweiX/IGEV.

cs.CV↗
arXiv2023

The multiplexed light storage of Orbital Angular Momentum based on atomic ensembles

The improvement of the multi-mode capability of quantum memory can further improve the utilization efficiency of the quantum memory and reduce the requirement of quantum communication for storage units. In this letter, we experimentally investigate the multi-mode light multiplexing storage of orbital angular momentum (OAM) mode based on rubidium vapor, and demultiplexing by a photonic OAM mode splitter which combines a Sagnac loop with two dove prisms. Our results show a mode extinction ratio higher than 80$\%$ at 1 $μ$s of storage time. Meanwhile, two OAM modes have been multiplexing stored and demultiplexed in our experimental configuration. We believe the experimental scheme may provide a possibility for high channel capacity and multi-mode quantum multiplexed quantum storage based on atomic ensembles.

physics.atom-ph↗
arXiv2023

CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction

In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability. The core of our CGI-Stereo is a Context and Geometry Fusion (CGF) block which adaptively fuses context and geometry information for more effective cost aggregation and meanwhile provides feedback to feature learning to guide more effective contextual feature extraction. The proposed CGF can be easily embedded into many existing stereo matching networks, such as PSMNet, GwcNet and ACVNet. The resulting networks show a significant improvement in accuracy. Specially, the model which incorporates our CGF with ACVNet ranks $1^{st}$ on the KITTI 2012 and 2015 leaderboards among all the published methods. We further propose an informative and concise cost volume, named Attention Feature Volume (AFV), which exploits a correlation volume as attention weights to filter a feature volume. Based on CGF and AFV, the proposed CGI-Stereo outperforms all other published real-time methods on KITTI benchmarks and shows better generalization ability than other real-time methods. Code is available at https://github.com/gangweiX/CGI-Stereo.

cs.CV↗
arXiv2023

Robust Multimodal Fusion for Human Activity Recognition

The proliferation of IoT and mobile devices equipped with heterogeneous sensors has enabled new applications that rely on the fusion of time-series data generated by multiple sensors with different modalities. While there are promising deep neural network architectures for multimodal fusion, their performance falls apart quickly in the presence of consecutive missing data and noise across multiple modalities/sensors, the issues that are prevalent in real-world settings. We propose Centaur, a multimodal fusion model for human activity recognition (HAR) that is robust to these data quality issues. Centaur combines a data cleaning module, which is a denoising autoencoder with convolutional layers, and a multimodal fusion module, which is a deep convolutional neural network with the self-attention mechanism to capture cross-sensor correlation. We train Centaur using a stochastic data corruption scheme and evaluate it on three datasets that contain data generated by multiple inertial measurement units. Centaur's data cleaning module outperforms 2 state-of-the-art autoencoder-based models and its multimodal fusion module outperforms 4 strong baselines. Compared to 2 related robust fusion architectures, Centaur is more robust, achieving 11.59-17.52% higher accuracy in HAR, especially in the presence of consecutive missing data in multiple sensor channels.

cs.LG↗
arXiv2023

Finite speed axially symmetric Navier-Stokes flows passing a cone

Let $D$ be the exterior of a cone inside a ball, with its altitude angle at most $π/6$ in $\mathbb{R}^3$, which touches the $x_3$ axis at the origin. For any initial value $v_0 = v_{0,r}e_{r} + v_{0,θ} e_θ + v_{0,3} e_{3}$ in a $C^2(\overline{D})$ class, which has the usual even-odd-odd symmetry in the $x_3$ variable and has the partial smallness only in the swirl direction: $ | r v_{0, θ} | \leq \frac{1}{100}$, the axially symmetric Navier-Stokes equations (ASNS) with Navier-Hodge-Lions slip boundary condition has a finite-energy solution that stays bounded for all time. In particular, no finite-time blowup of the fluid velocity occurs. Compared with standard smallness assumptions on the initial velocity, no size restriction is made on the components $v_{0,r}$ and $v_{0,3}$. In a broad sense, this result appears to solve $2/3$ of the regularity problem of ASNS in such domains in the class of solutions with the above symmetry. Equivalently, this result is connected to the general open question which asks that if an absolute smallness of one component of the initial velocity implies the global smoothness, see e.g. page 873 in \cite{CZZ17}. Our result seems to give a positive answer in a special setting. As a byproduct, we also construct an unbounded solution of the forced Navier Stokes equation in a special cusp domain that has finite energy. The forcing term, with the scaling factor of $-1$, is in the standard regularity class. This result confirms the intuition that if the channel of a fluid is very thin, arbitrarily high speed in the classical sense can be attained under a mildly singular force which is physically reasonable in view that Newtonian gravity and Coulomb force have scaling factor $-2$.

math.AP↗
arXiv2023

Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations

People break up, miscarry, and lose loved ones. Their online streaming and shopping recommendations, however, do not necessarily update, and may serve as unhappy reminders of their loss. When users want to renege on their past actions, they expect the recommender platforms to erase selective data at the model level. Ideally, given any specified user history, the recommender can unwind or "forget", as if the record was not part of training. To that end, this paper focuses on simple but widely deployed bi-linear models for recommendations based on matrix completion. Without incurring the cost of re-training, and without degrading the model unnecessarily, we develop Unlearn-ALS by making a few key modifications to the fine-tuning procedure under Alternating Least Squares optimisation, thus applicable to any bi-linear models regardless of the training procedure. We show that Unlearn-ALS is consistent with retraining without \emph{any} model degradation and exhibits rapid convergence, making it suitable for a large class of existing recommenders.

cs.LG↗
arXiv2023

Research on data integration of overseas discrete archives from the perspective of digital humanties

The digitization of displaced archives is of great historical and cultural significance. Through the construction of digital humanistic platforms represented by MISS platform, and the comprehensive application of IIIF technology, knowledge graph technology, ontology technology, and other popular information technologies. We can find that the digital framework of displaced archives built through the MISS platform can promote the establishment of a standardized cooperation and dialogue mechanism between the archives authoritiess and other government departments. At the same time, it can embed the works o fichives ction of digital government and the economy, promote the exploration of the integration of archives management, data management, and information resource management, and ultimately promote the construction of a digital society. By fostering a new partnership between archives departments and enterprises, think tanks, research institutes, and industry associations, the role of multiple social subjects in the modernization process of the archives governance system and governance capacity will be brought into play. The National Archives Administration has launched a special operation to recover scattered archives overseas, drawing up a list and a recovery action plan for archives lost to overseas institutions and individuals due to war and other reasons. Through the National Archives Administration, the State Administration of Cultural Heritage, the Ministry of Foreign Affairs, the Supreme People's Court, the Supreme People's Procuratorate, and the Ministry of Justice, specific recovery work is carried out by studying and working on international laws.

cs.SI↗
arXiv2023

Non-homogeneous boundary value problems for coupled KdV-KdV systems posed on the half line

In this article, we study an initial-boundary-value problem of a coupled KdV-KdV system on the half line $ \mathbb{R}^+ $ with non-homogeneous boundary conditions: \begin{equation*} \left\{ \begin{array}{l} u_t+v_x+u u_x+v_{xxx}=0, \quad v_t+u_x+(vu)_x+u_{xxx}=0, \quad u(x,0)=ϕ(x),\quad v(x,0)=ψ(x), \quad u(0,t)=h_1(t),\quad v(0,t)=h_2(t),\quad v_x(0,t)=h_3(t), \end{array} \right. \qquad x,\,t>0. \end{equation*} It is shown that the problem is locally unconditionally well-posed in $H^s(\mathbb{R}^+)\times H^s(\mathbb{R}^+)$ for $s> -\frac34 $ with initial data $(ϕ,ψ)$ in $H^s(\mathbb{R}^+)\times H^{s}(\mathbb{R}^+)$ and boundary data $(h_1,h_2,h_3) $ in $H^{\frac{s+1}{3}}(\mathbb{R}^+)\times H^{\frac{s+1}{3}}(\mathbb{R}^+)\times H^{\frac{s}{3}}(\mathbb{R}^+)$. The approach developed in this paper can also be applied to study more general KdV-KdV systems posed on the half line.

math.AP↗
arXiv2022

DPAUC: Differentially Private AUC Computation in Federated Learning

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on FL has mostly studied how to protect label privacy during model training. However, model evaluation in FL might also lead to potential leakage of private label information. In this work, we propose an evaluation algorithm that can accurately compute the widely used AUC (area under the curve) metric when using the label differential privacy (DP) in FL. Through extensive experiments, we show our algorithms can compute accurate AUCs compared to the ground truth. The code is available at {\url{https://github.com/bytedance/fedlearner/tree/master/example/privacy/DPAUC}}.

cs.LG↗
arXiv2022

Comparative study of machine learning and deep learning methods on ASD classification

The autism dataset is studied to identify the differences between autistic and healthy groups. For this, the resting-state Functional Magnetic Resonance Imaging (rs-fMRI) data of the two groups are analyzed, and networks of connections between brain regions were created. Several classification frameworks are developed to distinguish the connectivity patterns between the groups. The best models for statistical inference and precision were compared, and the tradeoff between precision and model interpretability was analyzed. Finally, the classification accuracy measures were reported to justify the performance of our framework. Our best model can classify autistic and healthy patients on the multisite ABIDE I data with 71% accuracy.

eess.IV↗
arXiv2022

Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation

Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the depth and background information during the domain feature alignment. A consistency loss between the generated depth and fog transmission map is introduced to strengthen the retention of the depth information in the aligned features. To address false object features potentially generated during the DA process, we propose an encoder-decoder framework to reconstruct the fog-free background image. This reconstruction loss also reinforces the encoder, i.e., our DA backbone, to minimize false object features.Moreover, we involve our target data in training both our DA module and our detection module in a semi-supervised manner, so that our detection module is also exposed to the unlabeled target data, the type of data used in the testing stage. Using these ideas, our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset), and obtains the best performance on multiple real-image public datasets. Code is available at: https://github.com/VIML-CVDL/Object-Detection-in-Foggy-Scenes

cs.CV↗
arXiv2022

Explore Contextual Information for 3D Scene Graph Generation

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task.

cs.CV↗
arXiv2022

Semantic Learning and Emulation Based Cross-platform Binary Vulnerability Seeker

Clone detection is widely exploited for software vulnerability search. The approaches based on source code analysis cannot be applied to binary clone detection because the same source code can produce significantly different binaries. In this paper, we present BinSeeker, a cross-platform binary seeker that integrates semantic learning and emulation. With the help of the labeled semantic flow graph, BinSeeker can quickly identify M candidate functions that are most similar to the vulnerability from the target binary. The value of M is relatively large so this semantic learning procedure essentially eliminates those functions that are very unlikely to have the vulnerability. Then, semantic emulation is conducted on these M candidates to obtain their dynamic signature sequences. By comparing signature sequences, BinSeeker produces top-N functions that exhibit most similar behavior to that of the vulnerability. With fast filtering of semantic learning and accurate comparison of semantic emulation, BinSeeker seeks vulnerability precisely with little overhead. The experiments on six widely used programs with fifteen known CVE vulnerabilities demonstrate that BinSeeker outperforms three state-of-the-art tools Genius, Gemini and CACompare. Regarding search accuracy, BinSeeker achieves an MRR value of 0.65 in the target programs, whereas the MRR values by Genius, Gemini and CACompare are 0.17, 0.07 and 0.42, respectively. If we consider ranking a function with the targeted vulnerability in the top-5 as accurate, BinSeeker achieves the accuracy of 93.33 percent, while the accuracy of the other three tools is merely 33.33, 13.33 and 53.33 percent, respectively. Such accuracy is achieved with 0.27s on average to determine whether the target binary function contains a known vulnerability, and the time for the other three tools are 1.57s, 0.15s and 0.98s, respectively.

cs.CR↗