Searcharxiv⌕ Search

arXiv subjects

Jun Zhang

Publications and source records attributed to Jun Zhang.

At least 685 records · Page 38Linked to original sources
arXiv2023

Alleviating both $H_0$ and $S_8$ tensions: early dark energy lifts the CMB-lockdown on ultralight axion

The existence of ultralight axion (ULA) with mass $\mathcal{O}( 10^{-26}\text{eV})$ is not favored by the CMB observations in the standard $Λ$CDM model. We show that the inclusion of early dark energy (EDE) will lift the CMB-lockdown on such ULA, and possibly other forms of dark matter beyond cold dark matter. By performing Monte Carlo Markov Chain analysis, it is found that, as opposed to $Λ$CDM, the AdS-EDE cosmology (with an Anti-de Sitter phase around recombination) now allows the existence of axion with mass $10^{-26}$ eV and predicts $6\%$ of the matter in our Universe to be such ULA, which can also help alleviating the $S_8$ tension in EDE.

astro-ph.CO↗
arXiv2023

Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance

Fusion-based hyperspectral image (HSI) super-resolution has become increasingly prevalent for its capability to integrate high-frequency spatial information from the paired high-resolution (HR) RGB reference image. However, most of the existing methods either heavily rely on the accurate alignment between low-resolution (LR) HSIs and RGB images, or can only deal with simulated unaligned RGB images generated by rigid geometric transformations, which weakens their effectiveness for real scenes. In this paper, we explore the fusion-based HSI super-resolution with real RGB reference images that have both rigid and non-rigid misalignments. To properly address the limitations of existing methods for unaligned reference images, we propose an HSI fusion network with heterogenous feature extractions, multi-stage feature alignments, and attentive feature fusion. Specifically, our network first transforms the input HSI and RGB images into two sets of multi-scale features with an HSI encoder and an RGB encoder, respectively. The features of RGB reference images are then processed by a multi-stage alignment module to explicitly align the features of RGB reference with the LR HSI. Finally, the aligned features of RGB reference are further adjusted by an adaptive attention module to focus more on discriminative regions before sending them to the fusion decoder to generate the reconstructed HR HSI. Additionally, we collect a real-world HSI fusion dataset, consisting of paired HSI and unaligned RGB reference, to support the evaluation of the proposed model for real scenes. Extensive experiments are conducted on both simulated and our real-world datasets, and it shows that our method obtains a clear improvement over existing single-image and fusion-based super-resolution methods on quantitative assessment as well as visual comparison.

cs.CV↗
arXiv2023

In-Context Learning with Many Demonstration Examples

Large pre-training language models (PLMs) have shown promising in-context learning abilities. However, due to the backbone transformer architecture, existing PLMs are bottlenecked by the memory and computational cost when scaling up to a large context size, leaving instruction tuning and in-context learning of many demonstration examples, as well as long-range language modeling under-explored. In this study, we propose a long-range language model EVALM based on an efficient transformer mechanism. EVALM is trained with 8k tokens per batch line and can test up to 256k-lengthed contexts with extrapolation, 128 times to the limit of existing PLMs (e.g. GPT3). Based on EVALM, we scale up the size of examples efficiently in both instruction tuning and in-context learning to explore the boundary of the benefits from more annotated data. Experimental results on a diverse set of tasks show that EVALM achieves 4.1% higher accuracy on average, and the average length of achieving the best accuracy score over tasks is around 12k. We find that in-context learning can achieve higher performance with more demonstrations under many-shot instruction tuning (8k), and further extending the length of instructions (16k) can further improve the upper bound of scaling in-context learning.

cs.CL↗
arXiv2023

Blind Performance Prediction for Deep Learning Based Ultra-Massive MIMO Channel Estimation

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to quantify due to the black-box nature of neural networks. This limitation is a major obstacle that hinders their practical deployment. In this paper, we attempt to quantify the uncertainty of an important category of DL-based channel estimators. An efficient statistical method is proposed to make blind predictions for the mean squared error of the DL-estimated channel solely based on received pilots, without knowledge of the ground-truth channel, the prior distribution of the channel, or the noise statistics. The complexity of the blind performance prediction is low and scales only linearly with the number of antennas. Simulation results for ultra-massive multiple-input multiple-output (UM-MIMO) channel estimation with a mixture of far-field and near-field paths are provided to verify the accuracy and efficiency of the proposed method.

eess.SP↗
arXiv2023

A Self-adaptive Neuroevolution Approach to Constructing Deep Neural Network Architectures Across Different Types

Neuroevolution has greatly promoted Deep Neural Network (DNN) architecture design and its applications, while there is a lack of methods available across different DNN types concerning both their scale and performance. In this study, we propose a self-adaptive neuroevolution (SANE) approach to automatically construct various lightweight DNN architectures for different tasks. One of the key settings in SANE is the search space defined by cells and organs self-adapted to different DNN types. Based on this search space, a constructive evolution strategy with uniform evolution settings and operations is designed to grow DNN architectures gradually. SANE is able to self-adaptively adjust evolution exploration and exploitation to improve search efficiency. Moreover, a speciation scheme is developed to protect evolution from early convergence by restricting selection competition within species. To evaluate SANE, we carry out neuroevolution experiments to generate different DNN architectures including convolutional neural network, generative adversarial network and long short-term memory. The results illustrate that the obtained DNN architectures could have smaller scale with similar performance compared to existing DNN architectures. Our proposed SANE provides an efficient approach to self-adaptively search DNN architectures across different types.

cs.NE↗
arXiv2023

Positively curved Kähler metrics on tube domains and their applications to optimal transport

In this article, we study a class of Kähler manifolds defined on tube domains in $\mathbb{C}^n$, and in particular those which have $O(n) \times \mathbb{R}^n$ symmetry. For these, we prove a uniqueness result showing that any such manifold which is complete and has non-negative orthogonal bisectional curvature ($n \geq 3$) or non-negative bisectional curvature ($n \geq 2$) is biholomorphically isometric to $\mathbb{C}^n$. We also consider another curvature tensor called the \emph{orthogonal anti-bisectional curvature}. We find necessary and sufficient conditions for a complete $O(n)$-symmetric tube domain to have non-negative orthogonal anti-bisectional curvature and provide several examples of complete metrics which satisfy this condition. Finally, we discuss some applications of these spaces within optimal transport. In particular, we study "synthetic" curvature bounds for non-smooth geometries and how they can be applied to the rough geometry induced by the Monge cost $c(x,y)=\|x-y\|$.

math.DG↗
arXiv2023

Sparse Mixture-of-Experts are Domain Generalizable Learners

Human visual perception can easily generalize to out-of-distributed visual data, which is far beyond the capability of modern machine learning models. Domain generalization (DG) aims to close this gap, with existing DG methods mainly focusing on the loss function design. In this paper, we propose to explore an orthogonal direction, i.e., the design of the backbone architecture. It is motivated by an empirical finding that transformer-based models trained with empirical risk minimization (ERM) outperform CNN-based models employing state-of-the-art (SOTA) DG algorithms on multiple DG datasets. We develop a formal framework to characterize a network's robustness to distribution shifts by studying its architecture's alignment with the correlations in the dataset. This analysis guides us to propose a novel DG model built upon vision transformers, namely Generalizable Mixture-of-Experts (GMoE). Extensive experiments on DomainBed demonstrate that GMoE trained with ERM outperforms SOTA DG baselines by a large margin. Moreover, GMoE is complementary to existing DG methods and its performance is substantially improved when trained with DG algorithms.

cs.CV↗
arXiv2023

Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into an informative and compact representation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.

eess.SP↗
arXiv2023

Artificial intelligence for diagnosing and predicting survival of patients with renal cell carcinoma: Retrospective multi-center study

Background: Clear cell renal cell carcinoma (ccRCC) is the most common renal-related tumor with high heterogeneity. There is still an urgent need for novel diagnostic and prognostic biomarkers for ccRCC. Methods: We proposed a weakly-supervised deep learning strategy using conventional histology of 1752 whole slide images from multiple centers. Our study was demonstrated through internal cross-validation and external validations for the deep learning-based models. Results: Automatic diagnosis for ccRCC through intelligent subtyping of renal cell carcinoma was proved in this study. Our graderisk achieved aera the curve (AUC) of 0.840 (95% confidence interval: 0.805-0.871) in the TCGA cohort, 0.840 (0.805-0.871) in the General cohort, and 0.840 (0.805-0.871) in the CPTAC cohort for the recognition of high-grade tumor. The OSrisk for the prediction of 5-year survival status achieved AUC of 0.784 (0.746-0.819) in the TCGA cohort, which was further verified in the independent General cohort and the CPTAC cohort, with AUC of 0.774 (0.723-0.820) and 0.702 (0.632-0.765), respectively. Cox regression analysis indicated that graderisk, OSrisk, tumor grade, and tumor stage were found to be independent prognostic factors, which were further incorporated into the competing-risk nomogram (CRN). Kaplan-Meier survival analyses further illustrated that our CRN could significantly distinguish patients with high survival risk, with hazard ratio of 5.664 (3.893-8.239, p < 0.0001) in the TCGA cohort, 35.740 (5.889-216.900, p < 0.0001) in the General cohort and 6.107 (1.815 to 20.540, p < 0.0001) in the CPTAC cohort. Comparison analyses conformed that our CRN outperformed current prognosis indicators in the prediction of survival status, with higher concordance index for clinical prognosis.

eess.IV↗
arXiv2023

GNN-Enhanced Approximate Message Passing for Massive/Ultra-Massive MIMO Detection

Efficient massive/ultra-massive multiple-input multiple-output (MIMO) detection algorithms with satisfactory performance and low complexity are critical to meet the high throughput and ultra-low latency requirements in 5G and beyond communications, given the extremely large number of antennas. In this paper, we propose a low-complexity graph neural network (GNN) enhanced approximate message passing (AMP) algorithm, AMP-GNN, for massive/ultra-massive MIMO detection. The structure of the neural network is customized by unfolding the AMP algorithm and introducing the GNN module for multiuser interference cancellation. Numerical results will show that the proposed AMP-GNN significantly improves the performance of the AMP detector and achieves comparable performance as the state-of-the-art deep learning-based MIMO detectors but with reduced computational complexity. Furthermore, it presents strong robustness to the change of the number of users.

cs.IT↗
arXiv2023

Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design

Federated learning (FL) is a powerful distributed machine learning framework where a server aggregates models trained by different clients without accessing their private data. Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server's access to many clients' data and the edge servers' closeness to the clients to achieve a high communication efficiency. Neural network quantization can further reduce the communication overhead during model uploading. To fully exploit the advantages of hierarchical FL, an accurate convergence analysis with respect to the key system parameters is needed. Unfortunately, existing analysis is loose and does not consider model quantization. In this paper, we derive a tighter convergence bound for hierarchical FL with quantization. The convergence result leads to practical guidelines for important design problems such as the client-edge aggregation and edge-client association strategies. Based on the obtained analytical results, we optimize the two aggregation intervals and show that the client-edge aggregation interval should slowly decay while the edge-cloud aggregation interval needs to adapt to the ratio of the client-edge and edge-cloud propagation delay. Simulation results shall verify the design guidelines and demonstrate the effectiveness of the proposed aggregation strategy.

cs.LG↗
arXiv2023

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, large-scale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms. The classic optimization-based algorithms usually require highly precise mathematical model of data links and suffer from poor performance with high computational cost in realistic 6G applications. Based on domain knowledge (e.g., optimization models and theoretical tools), machine learning (ML) stands out as a promising and viable methodology for many complex large-scale optimization problems in 6G, due to its superior performance, generalizability, computational efficiency and robustness. In this paper, we systematically review the most representative "learning to optimize" techniques in diverse domains of 6G wireless networks by identifying the inherent feature of the underlying optimization problem and investigating the specifically designed ML frameworks from the perspective of optimization. In particular, we will cover algorithm unrolling, learning to branch-and-bound, graph neural network for structured optimization, deep reinforcement learning for stochastic optimization, end-to-end learning for semantic optimization, as well as federated learning for distributed optimization, for solving challenging large-scale optimization problems arising from various important wireless applications. Through the in-depth discussion, we shed light on the excellent performance of ML-based optimization algorithms with respect to the classical methods, and provide insightful guidance to develop advanced ML techniques in 6G networks.

eess.SP↗
arXiv2022

GREAT3 results I: systematic errors in shear estimation and the impact of real galaxy morphology

We present first results from the third GRavitational lEnsing Accuracy Testing (GREAT3) challenge, the third in a sequence of challenges for testing methods of inferring weak gravitational lensing shear distortions from simulated galaxy images. GREAT3 was divided into experiments to test three specific questions, and included simulated space- and ground-based data with constant or cosmologically-varying shear fields. The simplest (control) experiment included parametric galaxies with a realistic distribution of signal-to-noise, size, and ellipticity, and a complex point spread function (PSF). The other experiments tested the additional impact of realistic galaxy morphology, multiple exposure imaging, and the uncertainty about a spatially-varying PSF; the last two questions will be explored in Paper II. The 24 participating teams competed to estimate lensing shears to within systematic error tolerances for upcoming Stage-IV dark energy surveys, making 1525 submissions overall. GREAT3 saw considerable variety and innovation in the types of methods applied. Several teams now meet or exceed the targets in many of the tests conducted (to within the statistical errors). We conclude that the presence of realistic galaxy morphology in simulations changes shear calibration biases by $\sim 1$ per cent for a wide range of methods. Other effects such as truncation biases due to finite galaxy postage stamps, and the impact of galaxy type as measured by the Sérsic index, are quantified for the first time. Our results generalize previous studies regarding sensitivities to galaxy size and signal-to-noise, and to PSF properties such as seeing and defocus. Almost all methods' results support the simple model in which additive shear biases depend linearly on PSF ellipticity.

astro-ph.CO↗
arXiv2022

Large-scale single-photon imaging

Benefiting from its single-photon sensitivity, single-photon avalanche diode (SPAD) array has been widely applied in various fields such as fluorescence lifetime imaging and quantum computing. However, large-scale high-fidelity single-photon imaging remains a big challenge, due to the complex hardware manufacture craft and heavy noise disturbance of SPAD arrays. In this work, we introduce deep learning into SPAD, enabling super-resolution single-photon imaging over an order of magnitude, with significant enhancement of bit depth and imaging quality. We first studied the complex photon flow model of SPAD electronics to accurately characterize multiple physical noise sources, and collected a real SPAD image dataset (64 $\times$ 32 pixels, 90 scenes, 10 different bit depth, 3 different illumination flux, 2790 images in total) to calibrate noise model parameters. With this real-world physical noise model, we for the first time synthesized a large-scale realistic single-photon image dataset (image pairs of 5 different resolutions with maximum megapixels, 17250 scenes, 10 different bit depth, 3 different illumination flux, 2.6 million images in total) for subsequent network training. To tackle the severe super-resolution challenge of SPAD inputs with low bit depth, low resolution, and heavy noise, we further built a deep transformer network with a content-adaptive self-attention mechanism and gated fusion modules, which can dig global contextual features to remove multi-source noise and extract full-frequency details. We applied the technique on a series of experiments including macroscopic and microscopic imaging, microfluidic inspection, and Fourier ptychography. The experiments validate the technique's state-of-the-art super-resolution SPAD imaging performance, with more than 5 dB superiority on PSNR compared to the existing methods.

physics.optics↗
arXiv2022

A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning

With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed. In this paper, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at \url{https://github.com/Xiaofeng-life/AwesomeDehazing}.

cs.CV↗
arXiv2022

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: \url{https://github.com/tencent-ailab/RLogist}.

cs.CV↗
arXiv2022

DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep Learning

The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field. However, a persistent issue remains unsolved during experiments: the interferential technical noise caused by systematic errors (e.g., temperature, reagent concentration, and well location) is always mixed up with the real biological signals, leading to misinterpretation of any conclusion drawn. Here, we show a mean teacher based deep learning model (DeepNoise) that can disentangle biological signals from the experimental noise. Specifically, we aim to classify the phenotypic impact of 1,108 different genetic perturbations screened from 125,510 fluorescent microscopy images, which are totally unrecognizable by human eye. We validate our model by participating in the Recursion Cellular Image Classification Challenge, and our proposed method achieves an extremely high classification score (Acc: 99.596%), ranking the 2nd place among 866 participating groups. This promising result indicates the successful separation of biological and technical factors, which might help decrease the cost of treatment development and expedite the drug discovery process.

eess.IV↗
arXiv2022

Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction

Temperature monitoring during the life time of heat source components in engineering systems becomes essential to guarantee the normal work and the working life of these components. However, prior methods, which mainly use the interpolate estimation to reconstruct the temperature field from limited monitoring points, require large amounts of temperature tensors for an accurate estimation. This may decrease the availability and reliability of the system and sharply increase the monitoring cost. To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly. First, we define the TFR-HSS task mathematically, and numerically model the task, and hence transform the task as an image-to-image regression problem. Then this work develops the deep reversible regression model which can better learn the physical information, especially over the boundary. Finally, considering the physical characteristics of heat conduction as well as the boundary conditions, this work proposes the physics-informed reconstruction loss including four training losses and jointly learns the deep surrogate model with these losses unsupervisedly. Experimental studies have conducted over typical two-dimensional heat-source systems to demonstrate the effectiveness of the proposed method.

cs.LG↗