arXiv subjects

Jin Chen

Publications and source records attributed to Jin Chen.

At least 91 records · Page 5Linked to original sources

arXiv2024

ChangeAnywhere: Sample Generation for Remote Sensing Change Detection via Semantic Latent Diffusion Model

Remote sensing change detection (CD) is a pivotal technique that pinpoints changes on a global scale based on multi-temporal images. With the recent expansion of deep learning, supervised deep learning-based CD models have shown satisfactory performance. However, CD sample labeling is very time-consuming as it is densely labeled and requires expert knowledge. To alleviate this problem, we introduce ChangeAnywhere, a novel CD sample generation method using the semantic latent diffusion model and single-temporal images. Specifically, ChangeAnywhere leverages the relative ease of acquiring large single-temporal semantic datasets to generate large-scale, diverse, and semantically annotated bi-temporal CD datasets. ChangeAnywhere captures the two essentials of CD samples, i.e., change implies semantically different, and non-change implies reasonable change under the same semantic constraints. We generated ChangeAnywhere-100K, the largest synthesis CD dataset with 100,000 pairs of CD samples based on the proposed method. The ChangeAnywhere-100K significantly improved both zero-shot and few-shot performance on two CD benchmark datasets for various deep learning-based CD models, as demonstrated by transfer experiments. This paper delineates the enormous potential of ChangeAnywhere for CD sample generation and demonstrates the subsequent enhancement of model performance. Therefore, ChangeAnywhere offers a potent tool for remote sensing CD. All codes and pre-trained models will be available at https://github.com/tangkai-RS/ChangeAnywhere.

cs.CV↗

arXiv2024

High Noise Scheduling is a Must

Consistency models possess high capabilities for image generation, advancing sampling steps to a single step through their advanced techniques. Current advancements move one step forward consistency training techniques and eliminates the limitation of distillation training. Even though the proposed curriculum and noise scheduling in improved training techniques yield better results than basic consistency models, it lacks well balanced noise distribution and its consistency between curriculum. In this study, it is investigated the balance between high and low noise levels in noise distribution and offered polynomial noise distribution to maintain the stability. This proposed polynomial noise distribution is also supported with a predefined Karras noises to prevent unique noise levels arises with Karras noise generation algorithm. Furthermore, by elimination of learned noisy steps with a curriculum based on sinusoidal function increase the performance of the model in denoising. To make a fair comparison with the latest released consistency model training techniques, experiments are conducted with same hyper-parameters except curriculum and noise distribution. The models utilized during experiments are determined with low depth to prove the robustness of our proposed technique. The results show that the polynomial noise distribution outperforms the model trained with log-normal noise distribution, yielding a 33.54 FID score after 100,000 training steps with constant discretization steps. Additionally, the implementation of a sinusoidal-based curriculum enhances denoising performance, resulting in a FID score of 30.48.

cs.LG↗

arXiv2024

A Shock Flash Breaking Out of a Dusty Red Supergiant

Shock breakout emission is light that arises when a shockwave, generated by core-collapse explosion of a massive star, passes through its outer envelope. Hitherto, the earliest detection of such a signal was at several hours after the explosion, though a few others had been reported. The temporal evolution of early light curves should reveal insights into the shock propagation, including explosion asymmetry and environment in the vicinity, but this has been hampered by the lack of multiwavelength observations. Here we report the instant multiband observations of a type II supernova (SN 2023ixf) in the galaxy M101 (at a distance of 6.85+/-0.15 Mpc), beginning at about 1.4 hours after the explosion. The exploding star was a red supergiant with a radius of about 440 solar radii. The light curves evolved rapidly, on timescales of 1-2 hours, and appeared unusually fainter and redder than predicted by models within the first few hours, which we attribute to an optically thick dust shell before it was disrupted by the shockwave. We infer that the breakout and perhaps the distribution of the surrounding dust were not spherically symmetric.

astro-ph.HE↗

arXiv2024

Disorder and diffuse scattering in single-chirality (TaSe$_4$)$_2$I crystals

The quasi-one-dimensional chiral compound (TaSe$_4$)$_2$I has been extensively studied as a prime example of a topological Weyl semimetal. Upon crossing its phase transition temperature $T_\textrm{CDW}$ $\approx$ 263 K, (TaSe$_4$)$_2$I exhibits incommensurate charge density wave (CDW) modulations described by the well-defined propagation vector $\sim$(0.05, 0.05, 0.11), oblique to the TaSe$_4$ chains. Although optical and transport properties greatly depend on chirality, there is no systematic report about chiral domain size for (TaSe$_4$)$_2$I. In this study, our single-crystal scattering refinements reveal a bulk iodine deficiency, and Flack parameter measurements on multiple crystals demonstrate that separate (TaSe$_4$)$_2$I crystals have uniform handedness, supported by direct imaging and helicity dependent THz emission spectroscopy. Our single-crystal X-ray scattering and calculated diffraction patterns identify multiple diffuse features and create a real-space picture of the temperature-dependent (TaSe$_4$)$_2$I crystal structure. The short-range diffuse features are present at room temperature and decrease in intensity as the CDW modulation develops. These transverse displacements, along with electron pinning from the iodine deficiency, help explain why (TaSe$_4$)$_2$I behaves as an electronic semiconductor at temperatures above and below $T_\textrm{CDW}$, despite a metallic band structure calculated from density functional theory of the ideal structure.

cond-mat.str-el↗

arXiv2024

Dual Auction Mechanism for Transaction Relay and Validation in Complex Wireless Blockchain Network

In traditional public blockchain networks, transaction fees are only allocated to full nodes (i.e., miners). However, the lack of relay rewards reduces the willingness of light nodes to relay transactions, especially in the energy-constrained complex wireless network. This paper proposes a novel dual auction mechanism to allocate transaction fees for relay and validation behaviors in the wireless blockchain network. The dual auction mechanism consists of two sub-auction stages: the relay sub-auction and the validation sub-auction. In the relay sub-auction, relay nodes choose transactions based rewards to forward. Besides, relay nodes adjust the relaying probability through a no-regret algorithm to improve efficiency. In the validation sub-auction, full nodes select transactions using Vickrey-Clarke-Grove (VCG) mechanism to construct the block. We prove that the designed dual auction mechanism is Incentive Compatibility (IC), Individual Rationality (IR), and Computational Efficiency (CE). We also derive the upper bound of the social welfare difference between the social optimal auction and our proposed one. Extensive simulation results demonstrate that the proposed dual auction mechanism decreases energy and bandwidth resource consumption and effectively improves social welfare without sacrificing the throughput and the security of the wireless blockchain network.

cs.NI↗

arXiv2024

Text2MDT: Extracting Medical Decision Trees from Medical Texts

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

cs.CL↗

arXiv2023

An Incremental Update Framework for Online Recommenders with Data-Driven Prior

Online recommenders have attained growing interest and created great revenue for businesses. Given numerous users and items, incremental update becomes a mainstream paradigm for learning large-scale models in industrial scenarios, where only newly arrived data within a sliding window is fed into the model, meeting the strict requirements of quick response. However, this strategy would be prone to overfitting to newly arrived data. When there exists a significant drift of data distribution, the long-term information would be discarded, which harms the recommendation performance. Conventional methods address this issue through native model-based continual learning methods, without analyzing the data characteristics for online recommenders. To address the aforementioned issue, we propose an incremental update framework for online recommenders with Data-Driven Prior (DDP), which is composed of Feature Prior (FP) and Model Prior (MP). The FP performs the click estimation for each specific value to enhance the stability of the training process. The MP incorporates previous model output into the current update while strictly following the Bayes rules, resulting in a theoretically provable prior for the robust update. In this way, both the FP and MP are well integrated into the unified framework, which is model-agnostic and can accommodate various advanced interaction models. Extensive experiments on two publicly available datasets as well as an industrial dataset demonstrate the superior performance of the proposed framework.

cs.IR↗

arXiv2023

Consistency between reflection M-EELS and optical spectroscopy measurements of the long-wavelength density response of Bi$_2$Sr$_2$CaCu$_2$O$_{8+x}$

The density fluctuation spectrum captures many fundamental properties of strange metals. Using momentum-resolved electron energy-loss spectroscopy (M-EELS), we recently showed that the density response of the strange metal Bi$_2$Sr$_2$CaCu$_2$O$_{8+x}$ (Bi-2212) at large momentum, $q$, exhibits a constant-in-frequency continuum [Mitrano, PNAS $\textbf{115}$, 5392 (2018); Husain, PRX $\textbf{9}$, 041062 (2019)] reminiscent of the marginal Fermi liquid (MFL) hypothesis of the late 1980s [Varma, PRL $\textbf{63}$, 1996 (1989)]. However, reconciling this observation with infrared (IR) optics experiments, which show a well-defined plasmon excitation at $q \sim 0$, has been challenging. Here we report M-EELS measurements of Bi-2212 using 4$\times$ improved momentum resolution, allowing us to reach the optical limit. For momenta $q<0.04$ r.l.u., the M-EELS data show a plasmon feature that is quantitatively consistent with IR optics. For $q>0.04$ r.l.u., the spectra become incoherent with an MFL-like, constant-in-frequency form. We speculate that, at finite frequency, $ω$, and nonzero $q$, some attribute of this Planckian metal randomizes the probe electron, causing it to lose information about its own momentum.

cond-mat.str-el↗

arXiv2023

Scaling up the formation of agents with heterogeneous sensing: mixed distance and bearing-only

Unlike the case with identical neighboring agents whose actions are mirrored, the problem of distributed formation control design with heterogeneous sensing is not straightforward. In this paper, we consider the problem of distributed formation control where each agent can only control distances or bearings with its neighbors. We firstly develop a rigidity theory with heterogeneous sensing to ensure that the desired shape is well-posed. Secondly, we propose an iterative method that allows us to scale up the number of agents with heterogeneous sensing. Finally, numerical simulations show the effectiveness of our method.

eess.SY↗

arXiv2023

Latent Diffusion Model for Medical Image Standardization and Enhancement

Computed tomography (CT) serves as an effective tool for lung cancer screening, diagnosis, treatment, and prognosis, providing a rich source of features to quantify temporal and spatial tumor changes. Nonetheless, the diversity of CT scanners and customized acquisition protocols can introduce significant inconsistencies in texture features, even when assessing the same patient. This variability poses a fundamental challenge for subsequent research that relies on consistent image features. Existing CT image standardization models predominantly utilize GAN-based supervised or semi-supervised learning, but their performance remains limited. We present DiffusionCT, an innovative score-based DDPM model that operates in the latent space to transform disparate non-standard distributions into a standardized form. The architecture comprises a U-Net-based encoder-decoder, augmented by a DDPM model integrated at the bottleneck position. First, the encoder-decoder is trained independently, without embedding DDPM, to capture the latent representation of the input data. Second, the latent DDPM model is trained while keeping the encoder-decoder parameters fixed. Finally, the decoder uses the transformed latent representation to generate a standardized CT image, providing a more consistent basis for downstream analysis. Empirical tests on patient CT images indicate notable improvements in image standardization using DiffusionCT. Additionally, the model significantly reduces image noise in SPAD images, further validating the effectiveness of DiffusionCT for advanced imaging tasks.

eess.IV↗

arXiv2023

D-type Minimal Conformal Matter: Quantum Curves, Elliptic Garnier Systems, and the 5d Descendants

We study the quantization of the 6d Seiberg-Witten curve for D-type minimal conformal matter theories compactified on a two-torus. The quantized 6d curve turns out to be a difference equation established via introducing codimension two and four surface defects. We show that, in the Nekrasov-Shatashvili limit, the 6d partition function with insertions of codimension two and four defects serve as the eigenfunction and eigenvalues of the difference equation, respectively. We further identify the quantum curve of D-type minimal conformal matters with an elliptic Garnier system recently studied in the integrability community. At last, as a concrete consequence of our elliptic quantum curve, we study its RG flows to obtain various quantum curves of 5d ${\rm Sp}(N)+N_f \mathsf{F},N_f\leq 2N+5$ theories.

hep-th↗

arXiv2023

When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities

The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.

cs.IR↗

arXiv2023

SymTFTs and Duality Defects from 6d SCFTs on 4-manifolds

In this work we study particular TQFTs in three dimensions, known as Symmetry Topological Field Theories (or SymTFTs), to identify line defects of two-dimensional CFTs arising from the compactification of 6d $(2,0)$ SCFTs on 4-manifolds $M_4$. The mapping class group of $M_4$ and the automorphism group of the SymTFT switch between different absolute 2d theories or global variants. Using the combined symmetries, we realize the topological defects in these global variants. Our main example is $\mathbb{P}^1 \times \mathbb{P}^1$. For $N$ M5-branes the corresponding 2d theory inherits $\mathbb{Z}_N$ $0$-form symmetries from the SymTFT. We reproduce the orbifold groupoid for theories with $\mathbb{Z}_N$ $0$-form symmetries and realize the duality defects at fixed points of the coupling constant under elements of the mapping class group. We also study other Hirzebruch surfaces, del Pezzo surfaces, as well as the connected sum of $\mathbb{P}^1 \times \mathbb{P}^1$. We find a rich network of global variants connected via automorphisms and realize more interesting topological defects. Finally, we derive the SymTFT on more general 4-manifolds and provide two examples.

hep-th↗

arXiv2023

A string-theoretical analog of non-maximal chaos in some Sachdev-Ye-Kitaev-like models

Very recently two of the present authors have studied the chaos exponent of some Sachdev-Ye-Kitaev (SYK)-like models for arbitrary interaction strength [1]. These models carry supersymmetric (SUSY) or SUSY-like structures. Namely, bosons and Majorana fermions are both present and each of them interacts with $(q-1)$ particles, but the model is not necessarily supersymmetric. It was found that the chaos exponents in different models, no matter whether they carry SUSY(-like) structures or not, all follow a universal single-parameter scaling law for large $q$, and by tuning that parameter continuously a flow from maximally chaotic to completely regular motion results. Here we report a string-theoretical analog of this chaotic phenomenon. Specifically, we consider closed string scattering near the two-sided AdS black hole, whose amplitude grows exponentially in the Schwarzschild time, with a rate determined by the Regge spin of the Pomeron exchanged during string scattering. We calculate the Pomeron Regge spin for strings of different types, including the bosonic string, the type II superstring and the heterotic superstring. We find that the Pomeron Regge spin also displays a single-parameter scaling behavior independent of string types, with the parameter depending on the string length and the length scale characterizing the spacetime curvature; moreover, the scaling function has the same limiting behaviors as that for the chaos exponent of SYK-like models. Remarkably, the flow from maximally chaotic to completely regular motion in SYK-like models corresponds to the flow of the Pomeron Regge spin from $2$ to $1$.

hep-th↗

arXiv2023

Forward-Forward Contrastive Learning

Medical image classification is one of the most important tasks for computer-aided diagnosis. Deep learning models, particularly convolutional neural networks, have been successfully used for disease classification from medical images, facilitated by automated feature learning. However, the diverse imaging modalities and clinical pathology make it challenging to construct generalized and robust classifications. Towards improving the model performance, we propose a novel pretraining approach, namely Forward Forward Contrastive Learning (FFCL), which leverages the Forward-Forward Algorithm in a contrastive learning framework--both locally and globally. Our experimental results on the chest X-ray dataset indicate that the proposed FFCL achieves superior performance (3.69% accuracy over ImageNet pretrained ResNet-18) over existing pretraining models in the pneumonia classification task. Moreover, extensive ablation experiments support the particular local and global contrastive pretraining design in FFCL.

cs.CV↗

arXiv2023

Bootstrap Generalization Ability from Loss Landscape Perspective

Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablation studies as well as visualizations. In addition, we apply this theory in the ECCV 2022 NICO Challenge1 and achieve the 3rd place without using any domain invariant methods.

cs.CV↗

arXiv2023

Meta-causal Learning for Single Domain Generalization

Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. In this paper, we propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation. Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training. We use the meta-knowledge to analyze the shift between the target and source domains during testing. Specifically, we perform multiple transformations on source data to generate the auxiliary domain, perform counterfactual inference to learn to discover the causal factors of the shift between the auxiliary and source domains, and incorporate the inferred causality into factor-aware domain alignments. Extensive experiments on several benchmarks of image classification show the effectiveness of our method.

cs.CV↗

arXiv2023

FRA-LSTM: A Vessel Trajectory Prediction Method Based on Fusion of the Forward and Reverse Sub-Network

In order to improve the vessel's capacity and ensure maritime traffic safety, vessel intelligent trajectory prediction plays an essential role in the vessel's smart navigation and intelligent collision avoidance system. However, current researchers only focus on short-term or long-term vessel trajectory prediction, which leads to insufficient accuracy of trajectory prediction and lack of in-depth mining of comprehensive historical trajectory data. This paper proposes an Automatic Identification System (AIS) data-driven long short-term memory (LSTM) method based on the fusion of the forward sub-network and the reverse sub-network (termed as FRA-LSTM) to predict the vessel trajectory. The forward sub-network in our method combines LSTM and attention mechanism to mine features of forward historical trajectory data. Simultaneously, the reverse sub-network combines bi-directional LSTM (BiLSTM) and attention mechanism to mine features of backward historical trajectory data. Finally, the final predicted trajectory is generated by fusing output features of the forward and reverse sub-network. Based on plenty of experiments, we prove that the accuracy of our proposed method in predicting short-term and mid-term trajectories has increased by 96.8% and 86.5% on average compared with the BiLSTM and Seq2seq. Furthermore, the average accuracy of our method is 90.1% higher than that of compared the BiLSTM and Seq2seq in predicting long-term trajectories.

cs.CY↗