arXiv subjects

Chao Chen

Publications and source records attributed to Chao Chen.

At least 775 records · Page 43Linked to original sources

arXiv2022

On the Convergence of Optimizing Persistent-Homology-Based Losses

Topological loss based on persistent homology has shown promise in various applications. A topological loss enforces the model to achieve certain desired topological property. Despite its empirical success, less is known about the optimization behavior of the loss. In fact, the topological loss involves combinatorial configurations that may oscillate during optimization. In this paper, we introduce a general purpose regularized topology-aware loss. We propose a novel regularization term and also modify existing topological loss. These contributions lead to a new loss function that not only enforces the model to have desired topological behavior, but also achieves satisfying convergence behavior. Our main theoretical result guarantees that the loss can be optimized efficiently, under mild assumptions.

cs.LG↗

arXiv2022

Multi-Class Cell Detection Using Spatial Context Representation

In digital pathology, both detection and classification of cells are important for automatic diagnostic and prognostic tasks. Classifying cells into subtypes, such as tumor cells, lymphocytes or stromal cells is particularly challenging. Existing methods focus on morphological appearance of individual cells, whereas in practice pathologists often infer cell classes through their spatial context. In this paper, we propose a novel method for both detection and classification that explicitly incorporates spatial contextual information. We use the spatial statistical function to describe local density in both a multi-class and a multi-scale manner. Through representation learning and deep clustering techniques, we learn advanced cell representation with both appearance and spatial context. On various benchmarks, our method achieves better performance than state-of-the-arts, especially on the classification task. We also create a new dataset for multi-class cell detection and classification in breast cancer and we make both our code and data publicly available.

cs.CV↗

arXiv2022

Open-source Framework for Transonic Boundary Layer Natural Transition Analysis over Complex Geometries in Nektar++

We introduce an open-source and unified framework for transition analysis for laminar boundary layer natural transition at transonic conditions and over complex geometries, where surface irregularities may be present. Different computational tools are integrated in the framework, and therefore overcomes the difficulties of two separate and usually quite disparate processes when using $e^N$ method for transition analysis. To generate a baseflow with desired pressure distribution, appropriate pressure compatible inflow boundary condition needs to be developed and enforced. We first derive the system for 1D numerical stability analysis for boundary conditions, and construct three types of pressure compatible inflow. We demonstrate that the entropy-pressure compatible inflow is stable unlike other choices. Compared with the steady baseflow computation, the unsteady simulation for the disturbance field is more challenging for compressible flows because of complex wave reflections, which can easily contaminate the results. We therefore introduce the two main sources of wave decontamination and corresponding methods to obtain clean signal. The workflow within the framework is then verified by computing the disturbance development in 2D flat plate boundary layer flows at Mach $0.8$. The $N$-factors over a clean flat plate and a flat plate with a forward-facing step are generated, and agree well with the results from the reference. Following the verified workflow, We then analyze the disturbance growth on a wing section of the CRM-NLF model. The N-factor on a 2D simulation is generated and studied.

physics.flu-dyn↗

arXiv2022

Nuclear Norm Maximization Based Curiosity-Driven Learning

To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\ell^2$ norm or variance to measure the exploration novelty, which will amplify the noise due to the square operation. In this paper, we address aforementioned challenges by proposing a novel curiosity leveraging the nuclear norm maximization (NNM), which can quantify the novelty of exploring the environment more accurately while providing high-tolerance to the noise and outliers. We conduct extensive experiments across a variety of benchmark environments and the results suggest that NNM can provide state-of-the-art performance compared with previous curiosity methods. On 26 Atari games subset, when trained with only intrinsic reward, NNM achieves a human-normalized score of 1.09, which doubles that of competitive intrinsic rewards-based approaches. Our code will be released publicly to enhance the reproducibility.

cs.LG↗

arXiv2022

Stable, entropy-pressure compatible subsonic Riemann boundary condition for embedded DG compressible flow simulations

One approach to reduce the cost to simulate transitional compressible boundary layer flow is to adopt a near body reduced domain with boundary conditions enforced to be compatible with a computationally cheaper 3D RANS simulation. In such an approach it is desirable to enforce a consistent pressure distribution which is not typically the case when using the standard Riemann inflow boundary condition. We revisit the Riemann problem adopted in many DG based high fidelity formulations. Through analysis of the 1D linearised Euler equations it is demonstrated that maintaining entropy compatibility with the RANS simulation is important for a stable solution. The maintenance of Riemann invariant at outflow leaves one condition that can be imposed at the inflow. Therefore the entropy-pressure enforcement is the only stable boundary condition to enforce a known pressure distribution. We further demonstrate that all the entropy compatible inflow Riemann boundary conditions are stable providing the invariant compatible Riemann outflow boundary condition is also respected. Although the entropy-pressure compatible Riemann inflow boundary condition is stable from the 1D analysis, 2D tests highlight divergence in the inviscid problem and neutrally stable wiggles in the velocity fields in viscous simulations around the stagnation point. A 2D analysis about a non-uniform baseflow assumption provides insight into this stability issue (ill-posedness) and motivate the use of a mix of inflow boundary conditions in this region of the flow. As a validation we apply the proposed boundary conditions to a reduced domain of a wing section normal to the leading-edge of the CRM-NLF model taken out of a full 3D RANS simulation at Mach 0.86 and a Reynolds number of 8.5 million. The results show that the entropy-pressure compatible Riemann inflow boundary condition leads to a good agreement in pressure distribution.

physics.flu-dyn↗

arXiv2022

Ultrahigh-energy Gamma Rays and Gravitational Waves from Primordial Exotic Stellar Bubbles

We put forward a novel class of exotic celestial objects that can be produced through phase transitions occurred in the primordial Universe. These objects appear as bubbles of stellar sizes and can be dominated by primordial black holes (PBHs). We report that, due to the processes of Hawking radiation and binary evolution of PBHs inside these stellar bubbles, both electromagnetic and gravitational radiations can be emitted that are featured on the gamma-ray spectra and stochastic gravitational waves (GWs). Our results reveal that, depending on the mass distribution, the exotic stellar bubbles consisting of PBHs provide not only a decent fit for the ultrahigh-energy gamma-ray spectrum reported by the recent LHAASO experiment, but also predict GW signals that are expected to be tested by the forthcoming GW surveys.

astro-ph.CO↗

arXiv2022

Search for $X(3872)\toπ^0χ_{c0}$ and $X(3872)\toππχ_{c0}$ at BESIII

Using 9.9 fb$^{-1}$ of $e^+e^-$ collision data collected by the BESIII detector at center-of-mass energies between 4.15 and 4.30 GeV, we search for the processes $e^+e^-\toγX(3872)$ with $X(3872)\rightarrowπ^0χ_{c0}$ and $X(3872)\rightarrowππχ_{c0}$. Depending on the fitting model, the statistical significance for $X(3872)\toπ^0χ_{c0}$ ranges from 1.3$σ$ to 2.8$σ$. We set upper limits (at 90\% C.L.) of $\frac{\mathcal{B}(X(3872)\rightarrowπ^0χ_{c0})}{\mathcal{B}(X(3872)\toπ^+π^-J/ψ)}<3.6$, $\frac{\mathcal{B}(X(3872)\rightarrowπ^+π^-χ_{c0})}{\mathcal{B}(X(3872)\toπ^+π^-J/ψ)}<0.68$, and $\frac{\mathcal{B}(X(3872)\rightarrowπ^0π^0χ_{c0})}{\mathcal{B}(X(3872)\toπ^+π^-J/ψ)}<1.7$. Combined with the BESIII measurement of $X(3872)\toπ^0χ_{c1}$, we also set an upper limit of $\frac{\mathcal{B}(X(3872)\rightarrowπ^0χ_{c0})}{\mathcal{B}(X(3872)\toπ^0χ_{c1})}<4.4$.

hep-ex↗

arXiv2022

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

cs.CV↗

arXiv2022

A Novel Framework for Characterization of Tumor-Immune Spatial Relationships in Tumor Microenvironment

Understanding the impact of tumor biology on the composition of nearby cells often requires characterizing the impact of biologically distinct tumor regions. Biomarkers have been developed to label biologically distinct tumor regions, but challenges arise because of differences in the spatial extent and distribution of differentially labeled regions. In this work, we present a framework for systematically investigating the impact of distinct tumor regions on cells near the tumor borders, accounting their cross spatial distributions. We apply the framework to multiplex immunohistochemistry (mIHC) studies of pancreatic cancer and show its efficacy in demonstrating how biologically different tumor regions impact the immune response in the tumor microenvironment. Furthermore, we show that the proposed framework can be extended to largescale whole slide image analysis.

q-bio.QM↗

arXiv2022

Accurate Fruit Localisation for Robotic Harvesting using High Resolution LiDAR-Camera Fusion

Accurate depth-sensing plays a crucial role in securing a high success rate of robotic harvesting in natural orchard environments. Solid-state LiDAR (SSL), a recently introduced LiDAR technique, can perceive high-resolution geometric information of the scenes, which can be potential utilised to receive accurate depth information. Meanwhile, the fusion of the sensory information from LiDAR and camera can significantly enhance the sensing ability of the harvesting robots. This work introduces a LiDAR-camera fusion-based visual sensing and perception strategy to perform accurate fruit localisation for a harvesting robot in the apple orchards. Two SOTA extrinsic calibration methods, target-based and targetless-based, are applied and evaluated to obtain the accurate extrinsic matrix between the LiDAR and camera. With the extrinsic calibration, the point clouds and color images are fused to perform fruit localisation using a one-stage instance segmentation network. Experimental shows that LiDAR-camera achieves better quality on visual sensing in the natural environments. Meanwhile, introducing the LiDAR-camera fusion largely improves the accuracy and robustness of the fruit localisation. Specifically, the standard deviations of fruit localisation by using LiDAR-camera at 0.5 m, 1.2 m, and 1.8 m are 0.245, 0.227, and 0.275 cm respectively. These measurement error is only one one fifth of that from Realsense D455. Lastly, we have attached our visualised point cloud to demonstrate the highly accurate sensing method.

cs.RO↗

arXiv2022

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

Scene Graph Generation (SGG) aims to build a structured representation of a scene using objects and pairwise relationships, which benefits downstream tasks. However, current SGG methods usually suffer from sub-optimal scene graph generation because of the long-tailed distribution of training data. To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation. Specifically, RTPB uses a distributed-based prior bias to improve models' detecting ability on less frequent relationships during training, thus improving the model generalizability on tail categories. In addition, to further explore the contextual information of objects and relationships, we design a contextual encoding backbone network, termed as Dual Transformer (DTrans). We perform extensive experiments on a very popular benchmark, VG150, to demonstrate the effectiveness of our method for the unbiased scene graph generation. In specific, our RTPB achieves an improvement of over 10% under the mean recall when applied to current SGG methods. Furthermore, DTrans with RTPB outperforms nearly all state-of-the-art methods with a large margin.

cs.CV↗

arXiv2022

Amplitude analysis and branching-fraction measurement of $D_{s}^{+} \to π^{+}π^{0}η^{\prime}$

Using data collected with the BESIII detector in $e^+e^-$ collisions at center-of-mass energies between 4.178 and 4.226 GeV and corresponding to 6.32~fb$^{-1}$ of integrated luminosity, we report the amplitude analysis and branching-fraction measurement of the $D^+_s \to π^+ π^0 η^{\prime}$ decay. We find that the dominant intermediate process is $D^+_s \toρ^+ η^{\prime}$ and the significances of other resonant and nonresonant processes are all less than $3σ$. The upper limits on the branching fractions of $S$-wave and $P$-wave nonresonant components are set to $0.10\%$ and $0.74\%$ at the $90\%$ confidence level, respectively. In addition, the branching fraction of the $D^+_s \to π^+ π^0 η^{\prime}$ decay is measured to be $(6.15\pm0.25(\rm stat.)\pm0.18(\rm syst.))\%$, which receives significant contribution only from $D_s^+\to ρ^+η^{\prime}$ according to the amplitude analysis.

hep-ex↗

arXiv2022

A Manifold View of Adversarial Risk

The adversarial risk of a machine learning model has been widely studied. Most previous works assume that the data lies in the whole ambient space. We propose to take a new angle and take the manifold assumption into consideration. Assuming data lies in a manifold, we investigate two new types of adversarial risk, the normal adversarial risk due to perturbation along normal direction, and the in-manifold adversarial risk due to perturbation within the manifold. We prove that the classic adversarial risk can be bounded from both sides using the normal and in-manifold adversarial risks. We also show with a surprisingly pessimistic case that the standard adversarial risk can be nonzero even when both normal and in-manifold risks are zero. We finalize the paper with empirical studies supporting our theoretical results. Our results suggest the possibility of improving the robustness of a classifier by only focusing on the normal adversarial risk.

cs.LG↗

arXiv2022

Trigger Hunting with a Topological Prior for Trojan Detection

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan detection, namely, identifying Trojaned models -- models trained with poisoned data. One popular approach is reverse engineering, i.e., recovering the triggers on a clean image by manipulating the model's prediction. One major challenge of reverse engineering approach is the enormous search space of triggers. To this end, we propose innovative priors such as diversity and topological simplicity to not only increase the chances of finding the appropriate triggers but also improve the quality of the found triggers. Moreover, by encouraging a diverse set of trigger candidates, our method can perform effectively in cases with unknown target labels. We demonstrate that these priors can significantly improve the quality of the recovered triggers, resulting in substantially improved Trojan detection accuracy as validated on both synthetic and publicly available TrojAI benchmarks.

cs.CV↗

arXiv2022

Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation

Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms -- including both shallow and deep ones -- often model such dynamics independently, i.e., user static and dynamic preferences are not modeled under the same latent space, which makes it difficult to fuse them for recommendation. This paper considers the problem of embedding a user's sequential behavior into the latent space of user preferences, namely translating sequence to preference. To this end, we formulate the sequential recommendation task as a dictionary learning problem, which learns: 1) a shared dictionary matrix, each row of which represents a partial signal of user dynamic preferences shared across users; and 2) a posterior distribution estimator using a deep autoregressive model integrated with Gated Recurrent Unit (GRU), which can select related rows of the dictionary to represent a user's dynamic preferences conditioned on his/her past behaviors. Qualitative studies on the Netflix dataset demonstrate that the proposed method can capture the user preference drifts over time and quantitative studies on multiple real-world datasets demonstrate that the proposed method can achieve higher accuracy compared with state-of-the-art factorization and neural sequential recommendation methods. The code is available at https://github.com/cchao0116/S2PNM-TKDE2021.

cs.IR↗

arXiv2022

Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations

Clinical outcome or severity prediction from medical images has largely focused on learning representations from single-timepoint or snapshot scans. It has been shown that disease progression can be better characterized by temporal imaging. We therefore hypothesized that outcome predictions can be improved by utilizing the disease progression information from sequential images. We present a deep learning approach that leverages temporal progression information to improve clinical outcome predictions from single-timepoint images. In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory. Meanwhile, a Vision Transformer is pretrained in a self-supervised fashion to extract features from single-timepoint images. The key contribution is to design a recalibration module that employs maximum mean discrepancy loss (MMD) to align distributions of the above two contextual representations. We train our system to predict clinical outcomes and severity grades from single-timepoint images. Experiments on chest and osteoarthritis radiography datasets demonstrate that our approach outperforms other state-of-the-art techniques.

eess.IV↗

arXiv2022

Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are widely adopted for its effectiveness and relative simplicity. Despite being extensively studied, existing attentions still suffer from two limitations: i) conventional attentions mainly take into account the spatial correlation between user behaviors, regardless the distance between those behaviors in the continuous time space; and ii) these attentions mostly provide a dense and undistinguished distribution over all past behaviors then attentively encode them into the output latent representations. This is however not suitable in practical scenarios where a user's future actions are relevant to a small subset of her/his historical behaviors. In this paper, we propose a novel attention network, named self-modulating attention, that models the complex and non-linearly evolving dynamic user preferences. We empirically demonstrate the effectiveness of our method on top-N sequential recommendation tasks, and the results on three large-scale real-world datasets show that our model can achieve state-of-the-art performance.

cs.IR↗

arXiv2022

Discovering Governing Equations by Machine Learning implemented with Invariance

The partial differential equation (PDE) plays a significantly important role in many fields of science and engineering. The conventional case of the derivation of PDE mainly relies on first principles and empirical observation. However, the development of machine learning technology allows us to mine potential control equations from the massive amounts of stored data in a fresh way. Although there has been considerable progress in the data-driven discovery of PDE, the extant literature mostly focuses on the improvements of discovery methods, without substantial breakthroughs in the discovery process itself, including the principles for the construction of candidates and how to incorporate physical priors. In this paper, through rigorous derivation of formulas, novel physically enhanced machining learning discovery methods for control equations: GSNN (Galileo Symbolic Neural Network) and LSNN (Lorentz Symbolic Neural Network) are firstly proposed based on Galileo invariance and Lorentz invariance respectively, setting forth guidelines for building the candidates of discovering equations. The adoption of mandatory embedding of physical constraints is fundamentally different from PINN in the form of the loss function, thus ensuring that the designed Neural Network strictly obeys the physical prior of invariance and enhancing the interpretability of the network. By comparing the results with PDE-NET in numerical experiments of Burgers equation and Sine-Gordon equation, it shows that the method presented in this study has better accuracy, parsimony, and interpretability.

cs.LG↗