arXiv subjects

Geng Chen

Publications and source records attributed to Geng Chen.

At least 73 records · Page 4Linked to original sources

arXiv2024

Towards Accurate Camouflaged Object Detection with Mixture Convolution and Interactive Fusion

Camouflaged object detection (COD), which aims to identify the objects that conceal themselves into the surroundings, has recently drawn increasing research efforts in the field of computer vision. In practice, the success of deep learning based COD is mainly determined by two key factors, including (i) A significantly large receptive field, which provides rich context information, and (ii) An effective fusion strategy, which aggregates the rich multi-level features for accurate COD. Motivated by these observations, in this paper, we propose a novel deep learning based COD approach, which integrates the large receptive field and effective feature fusion into a unified framework. Specifically, we first extract multi-level features from a backbone network. The resulting features are then fed to the proposed dual-branch mixture convolution modules, each of which utilizes multiple asymmetric convolutional layers and two dilated convolutional layers to extract rich context features from a large receptive field. Finally, we fuse the features using specially-designed multilevel interactive fusion modules, each of which employs an attention mechanism along with feature interaction for effective feature fusion. Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context information from a large receptive field. All of these designs meet the requirements of COD well, allowing the accurate detection of camouflaged objects. Extensive experiments on widely-used benchmark datasets demonstrate that our method is capable of accurately detecting camouflaged objects and outperforms the state-of-the-art methods.

cs.CV↗

arXiv2024

CC-DCNet: Dynamic Convolutional Neural Network with Contrastive Constraints for Identifying Lung Cancer Subtypes on Multi-modality Images

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for clinical diagnosis. However, the majority of existing models rely solely on single-modality image input, leading to limited diagnostic accuracy. To this end, we propose a novel deep learning network designed to accurately classify lung cancer subtype with multi-dimensional and multi-modality images, i.e., CT and pathological images. The strength of the proposed model lies in its ability to dynamically process both paired CT-pathological image sets as well as independent CT image sets, and consequently optimize the pathology-related feature extractions from CT images. This adaptive learning approach enhances the flexibility in processing multi-dimensional and multi-modality datasets and results in performance elevating in the model testing phase. We also develop a contrastive constraint module, which quantitatively maps the cross-modality associations through network training, and thereby helps to explore the "gold standard" pathological information from the corresponding CT scans. To evaluate the effectiveness, adaptability, and generalization ability of our model, we conducted extensive experiments on a large-scale multi-center dataset and compared our model with a series of state-of-the-art classification models. The experimental results demonstrated the superiority of our model for lung cancer subtype classification, showcasing significant improvements in accuracy metrics such as ACC, AUC, and F1-score.

eess.IV↗

arXiv2024

Directly Estimating Mixed-State Entanglement with Bell Measurement Assistance

Entanglement plays a fundamental role in quantum physics and information processing. Here, we develop an unbiased estimator for mixed-state entanglement in the few-shot scenario and directly estimate it using random unitary evolution in a photonic system. As a supplement to traditional projective measurements, we incorporate Bell measurements on qubit-pairs, enriching the previous randomized measurement scheme, which is no-go in this task with only local unitary evolution. The scheme is scalable to n-qubits via Bell measurements on qubit-pairs. The estimator can be derived directly from a few consecutive outcomes while exhibiting greater robustness to system errors and noise compared to schemes based on shadow estimation. We find that, under a fixed measurement resource, the way with more versatile measurement settings with fewer repeats per setting is more efficient. Our protocol and demonstration advance the direct characterization of quantum states in practice.

quant-ph↗

arXiv2024

Learning Planning Abstractions from Language

This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover a symbolic and abstract action space and induce a latent state abstraction based on it. PARL consists of three stages: 1) recovering object-level and action concepts, 2) learning state abstractions, abstract action feasibility, and transition models, and 3) applying low-level policies for abstract actions. During inference, given the task description, PARL first makes abstract action plans using the latent transition and feasibility functions, then refines the high-level plan using low-level policies. PARL generalizes across scenarios involving novel object instances and environments, unseen concept compositions, and tasks that require longer planning horizons than settings it is trained on.

cs.RO↗

arXiv2024

Global solution and singularity formation for the supersonic expanding wave of compressible Euler equations with radial symmetry

In this paper, we define the rarefaction and compression characters for the supersonic expanding wave of the compressible Euler equations with radial symmetry. Under this new definition, we show that solutions with rarefaction initial data will not form shock in finite time, i.e. exist global-in-time as classical solutions. On the other hand, singularity forms in finite time when the initial data include strong compression somewhere. Several useful invariant domains will be also given.

math.AP↗

arXiv2024

Metadata-Driven Federated Learning of Connectional Brain Templates in Non-IID Multi-Domain Scenarios

A connectional brain template (CBT) is a holistic representation of a population of multi-view brain connectivity graphs, encoding shared patterns and normalizing typical variations across individuals. The federation of CBT learning allows for an inclusive estimation of the representative center of multi-domain brain connectivity datasets in a fully data-preserving manner. However, existing methods overlook the non-independent and identically distributed (non-IDD) issue stemming from multidomain brain connectivity heterogeneity, in which data domains are drawn from different hospitals and imaging modalities. To overcome this limitation, we unprecedentedly propose a metadata-driven federated learning framework, called MetaFedCBT, for cross-domain CBT learning. Given the data drawn from a specific domain (i.e., hospital), our model aims to learn metadata in a fully supervised manner by introducing a local client-based regressor network. The generated meta-data is forced to meet the statistical attributes (e.g., mean) of other domains, while preserving their privacy. Our supervised meta-data generation approach boosts the unsupervised learning of a more centered, representative, and holistic CBT of a particular brain state across diverse domains. As the federated learning progresses over multiple rounds, the learned metadata and associated generated connectivities are continuously updated to better approximate the target domain information. MetaFedCBT overcomes the non-IID issue of existing methods by generating informative brain connectivities for privacy-preserving holistic CBT learning with guidance using metadata. Extensive experiments on multi-view morphological brain networks of normal and patient subjects demonstrate that our MetaFedCBT is a superior federated CBT learning model and significantly advances the state-of-the-art performance.

cs.CV↗

arXiv2024

Existence and regularity for global solutions including breaking waves from Camassa-Holm and Novikov equations to $λ$-family equations

In this paper, we prove the global existence of Hölder continuous solutions for the Cauchy problem of a family of partial differential equations, named as $λ$-family equations, where $λ$ is the power of nonlinear wave speed. The $λ$-family equations include Camassa-Holm equation ($λ=1$) and Novikov equation ($λ=2$) modelling water waves, where solutions generically form finite time cusp singularities, or in another word, show wave breaking phenomenon. The global energy conservative solution we construct is Hölder continuous with exponent $1- \frac{1}{2λ}$. The existence result also paves the way for the future study on uniqueness and Lipschitz continuous dependence.

math.AP↗

arXiv2024

MAST: Video Polyp Segmentation with a Mixture-Attention Siamese Transformer

Accurate segmentation of polyps from colonoscopy videos is of great significance to polyp treatment and early prevention of colorectal cancer. However, it is challenging due to the difficulties associated with modelling long-range spatio-temporal relationships within a colonoscopy video. In this paper, we address this challenging task with a novel Mixture-Attention Siamese Transformer (MAST), which explicitly models the long-range spatio-temporal relationships with a mixture-attention mechanism for accurate polyp segmentation. Specifically, we first construct a Siamese transformer architecture to jointly encode paired video frames for their feature representations. We then design a mixture-attention module to exploit the intra-frame and inter-frame correlations, enhancing the features with rich spatio-temporal relationships. Finally, the enhanced features are fed to two parallel decoders for predicting the segmentation maps. To the best of our knowledge, our MAST is the first transformer model dedicated to video polyp segmentation. Extensive experiments on the large-scale SUN-SEG benchmark demonstrate the superior performance of MAST in comparison with the cutting-edge competitors. Our code is publicly available at https://github.com/Junqing-Yang/MAST.

cs.CV↗

arXiv2023

Multi-Level Knowledge Distillation for Speech Emotion Recognition in Noisy Conditions

Speech emotion recognition (SER) performance deteriorates significantly in the presence of noise, making it challenging to achieve competitive performance in noisy conditions. To this end, we propose a multi-level knowledge distillation (MLKD) method, which aims to transfer the knowledge from a teacher model trained on clean speech to a simpler student model trained on noisy speech. Specifically, we use clean speech features extracted by the wav2vec-2.0 as the learning goal and train the distil wav2vec-2.0 to approximate the feature extraction ability of the original wav2vec-2.0 under noisy conditions. Furthermore, we leverage the multi-level knowledge of the original wav2vec-2.0 to supervise the single-level output of the distil wav2vec-2.0. We evaluate the effectiveness of our proposed method by conducting extensive experiments using five types of noise-contaminated speech on the IEMOCAP dataset, which show promising results compared to state-of-the-art models.

cs.SD↗

arXiv2023

Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes

Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality volumes to thick-slice scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans. Extensive experiments on a large-scale dataset of 372 clinically acquired thick-slice MR scans demonstrate that our C2DA-Net achieves much better performance than cutting-edge methods quantitatively and qualitatively.

eess.IV↗

arXiv2023

BV solutions to a hyperbolic system of balance laws with logistic growth

We study BV solutions for a $2\times2$ system of hyperbolic balance laws. We show that when initial data have small total variation on $(-\infty,\infty)$ and small amplitude, and decay sufficiently fast to a constant equilibrium state as $|x|\rightarrow\infty$, a Cauchy problem (with generic data) has a unique admissible BV solution defined globally in time. Here the solution is admissible in the sense that its shock waves satisfy the Lax entropy condition. We also study asymptotic behavior of solutions. In particular, we obtain a time decay rate for the total variation of the solution, and a convergence rate of the solution to its time asymptotic solution. Our system is a modification of a Keller-Segel type chemotaxis model. Its flux function possesses new features when comparing to the well-known model of Euler equations with damping. This may help to shed light on how to extend the study to a general system of hyperbolic balance laws in the future.

math.AP↗

arXiv2023

The Poiseuille flow of the full Ericksen-Leslie model for nematic liquid crystals: The general Case

In this work, we study the Cauchy problem of Poiseuille flow of the full Ericksen-Leslie model for nematic liquid crystals. The model is a coupled system of two partial differential equations: One is a quasi-linear wave equation for the director field representing the crystallization of the nematics, and the other is a parabolic PDE for the velocity field characterizing the liquidity of the material. We extend the work in [Chen, et. al. {\em Arch. Ration. Mech. Anal.} {\bf 236} (2020), 839-891] for a special case to the general physical setup. The Cauchy problem is shown to have global solutions beyond singularity formation. Among a number of progresses made in this paper, a particular contribution is a systematic treatment of a parabolic PDE with only Hölder continuous diffusion coefficient and rough (worse than Hölder) nonhomogeneous terms.

math.AP↗

arXiv2023

Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify camouflaged objects with complete and fine details, while the boundary can not be well located for the lack of object-related semantics. In this paper, we propose a novel ``pre-train, adapt and detect" paradigm to detect camouflaged objects. By introducing a large pre-trained model, abundant knowledge learned from massive multi-modal data can be directly transferred to COD. A lightweight parallel adapter is inserted to adjust the features suitable for the downstream COD task. Extensive experiments on four challenging benchmark datasets demonstrate that our method outperforms existing state-of-the-art COD models by large margins. Moreover, we design a multi-task learning scheme for tuning the adapter to exploit the shareable knowledge across different semantic classes. Comprehensive experimental results showed that the generalization ability of our model can be substantially improved with multi-task adapter initialization on source tasks and multi-task adaptation on target tasks.

cs.CV↗

arXiv2023

Counterfactual communication without a trace in the transmission channel

We report an experimental realization of a modified counterfactual communication protocol that eliminates the dominant environmental trace left by photons passing through the transmission channel. Compared to Wheeler's criterion for inferring past particle paths, as used in prior protocols, our trace criterion provide stronger support for the claim of the counterfactuality of the communication. We verify the lack of trace left by transmitted photons via tagging the propagation arms of an interferometric device by distinct frequency-shifts and finding that the collected photons have no frequency shift which corresponds to the transmission channel. As a proof of principle, we counterfactually transfer a quick response code image with sufficient fidelity to be scanned with a cell phone.

quant-ph↗

arXiv2023

Classification of lung cancer subtypes on CT images with synthetic pathological priors

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score.

eess.IV↗

arXiv2023

Generic Singularities for 2D Pressureless Flow

In this paper, we consider the Cauchy problem for pressureless gases in two space dimensions with generic smooth initial data (density and velocity). These equations give rise to singular curves, where the mass has positive density w.r.t.~1-dimensional Hausdorff measure. We observe that the system of equations describing these singular curves is not hyperbolic. For analytic data, local solutions are constructed using a version of the Cauchy-Kovalevskaya theorem. We then study the interaction of two singular curves, in generic position. Finally, for a generic initial velocity field, we investigate the asymptotic structure of the smooth solution up to the first time when a singularity is formed.

math.AP↗

arXiv2023

Zipper: Addressing degeneracy in algorithm-agnostic inference

The widespread use of black box prediction methods has sparked an increasing interest in algorithm/model-agnostic approaches for quantifying goodness-of-fit, with direct ties to specification testing, model selection and variable importance assessment. A commonly used framework involves defining a predictiveness criterion, applying a cross-fitting procedure to estimate the predictiveness, and utilizing the difference in estimated predictiveness between two models as the test statistic. However, even after standardization, the test statistic typically fails to converge to a non-degenerate distribution under the null hypothesis of equal goodness, leading to what is known as the degeneracy issue. To addresses this degeneracy issue, we present a simple yet effective device, Zipper. It draws inspiration from the strategy of additional splitting of testing data, but encourages an overlap between two testing data splits in predictiveness evaluation. Zipper binds together the two overlapping splits using a slider parameter that controls the proportion of overlap. Our proposed test statistic follows an asymptotically normal distribution under the null hypothesis for any fixed slider value, guaranteeing valid size control while enhancing power by effective data reuse. Finite-sample experiments demonstrate that our procedure, with a simple choice of the slider, works well across a wide range of settings.

stat.ME↗

arXiv2023

Initial-boundary value problems for Poiseuille flow of nematic liquid crystal via full Ericksen-Leslie model

In this paper, we study the initial-boundary value problem for the Poiseuille flow of hyperbolic-parabolic Ericksen-Leslie model of nematic liquid crystals in one space dimension. Due to the quasilinearity, the solution of this model in general forms cusp singularity. We prove the global existence of Hölder continuous solution, which may include cusp singularity, for initial-boundary value problems with different types of boundary conditions.

math.AP↗