arXiv subjects

Junhao Lu

Publications and source records attributed to Junhao Lu.

11 recordsLinked to original sources

arXiv2026

Accuracy-Configurable Floating-Point Multiplier Design for SRAM-Based Compute-in-Memory

Digital Compute-in-Memory (DCiM) reduces data movement and has become a promising solution for energy-efficient edge AI. However, most existing DCiM frameworks still primarily target integer or fixed-point arithmetic, and provide limited support for compiler-integrated and accuracy-configurable floating-point computation. Directly integrating conventional IEEE 754 floating-point units into dense SRAM-based DCiM arrays, however, incurs high area and power overhead. To address this challenge, this work presents an accuracy-configurable floating-point multiplier integrated into the OpenACM framework for SRAM-based DCiM. An exact IEEE~754-compliant multiplier is first implemented as a baseline, and a mantissa-segmentation-based approximate multiplier is then proposed to reduce hardware cost while preserving numerical fidelity. Post-layout results show up to 69% logic area reduction and 72% power savings over exact floating-point designs without delay overhead. Evaluations on image processing tasks and ResNet-18 inference further demonstrate negligible accuracy degradation. These results indicate that compiler-integrated approximate floating-point multiplication is a practical approach for enabling efficient and configurable floating-point support in SRAM-based DCiM systems. The Floating-Point Multiplier is available on https://github.com/ShenShan123/OpenACM

cs.AR↗

arXiv2026

SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification

Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination). To mitigate these issues and enhance LLM performance in ECI, we propose SERE, a structural example retrieval framework that leverages LLMs' few-shot learning capabilities. SERE introduces an innovative retrieval mechanism based on three structural concepts: (i) Conceptual Path Metric, which measures the conceptual relationship between events using edit distance in ConceptNet; (ii) Syntactic Metric, which quantifies structural similarity through tree edit distance on syntactic trees; and (iii) Causal Pattern Filtering, which filters examples based on predefined causal structures using LLMs. By integrating these structural retrieval strategies, SERE selects more relevant examples to guide LLMs in causal reasoning, mitigating bias and improving accuracy in ECI tasks. Extensive experiments on multiple ECI datasets validate the effectiveness of SERE. The source code is publicly available at https://github.com/DMIRLAB-Group/SERE.

cs.CL↗

arXiv2026

Human Identification at a Distance: Challenges, Methods and Results on the Competition HID 2025

Human identification at a distance (HID) is challenging because traditional biometric modalities such as face and fingerprints are often difficult to acquire in real-world scenarios. Gait recognition provides a practical alternative, as it can be captured reliably at a distance. To promote progress in gait recognition and provide a fair evaluation platform, the International Competition on Human Identification at a Distance (HID) has been organized annually since 2020. Since 2023, the competition has adopted the challenging SUSTech-Competition dataset, which features substantial variations in clothing, carried objects, and view angles. No dedicated training data are provided, requiring participants to train their models using external datasets. Each year, the competition applies a different random seed to generate distinct evaluation splits, which reduces the risk of overfitting and supports a fair assessment of cross-domain generalization. While HID 2023 and HID 2024 already used this dataset, HID 2025 explicitly examined whether algorithmic advances could surpass the accuracy limits observed previously. Despite the heightened difficulty, participants achieved further improvements, and the best-performing method reached 94.2% accuracy, setting a new benchmark on this dataset. We also analyze key technical trends and outline potential directions for future research in gait recognition.

cs.CV↗

arXiv2025

CGTGait: Collaborative Graph and Transformer for Gait Emotion Recognition

Skeleton-based gait emotion recognition has received significant attention due to its wide-ranging applications. However, existing methods primarily focus on extracting spatial and local temporal motion information, failing to capture long-range temporal representations. In this paper, we propose \textbf{CGTGait}, a novel framework that collaboratively integrates graph convolution and transformers to extract discriminative spatiotemporal features for gait emotion recognition. Specifically, CGTGait consists of multiple CGT blocks, where each block employs graph convolution to capture frame-level spatial topology and the transformer to model global temporal dependencies. Additionally, we introduce a Bidirectional Cross-Stream Fusion (BCSF) module to effectively aggregate posture and motion spatiotemporal features, facilitating the exchange of complementary information between the two streams. We evaluate our method on two widely used datasets, Emotion-Gait and ELMD, demonstrating that our CGTGait achieves state-of-the-art or at least competitive performance while reducing computational complexity by approximately \textbf{82.2\%} (only requiring 0.34G FLOPs) during testing. Code is available at \small{https://github.com/githubzjj1/CGTGait.}

cs.CV↗

arXiv2025

Improving Photometric Redshift Estimation for CSST Mock Catalog Using SED Templates Calibrated with Perturbation Algorithm

Photometric redshifts of galaxies obtained by multi-wavelength data are widely used in photometric surveys because of its high efficiency. Although various methods have been developed, template fitting is still adopted as one of the most popular approaches. Its accuracy strongly depends on the quality of the Spectral Energy Distribution (SED) templates, which can be calibrated using broadband photometric data from galaxies with known spectroscopic redshifts. Such calibration is expected to improve photometric redshift accuracy, as the calibrated templates will align with observed photometric data more closely. The upcoming China Space Station Survey Telescope (CSST) is one of the Stage IV surveys, which aiming for high precision cosmological studies. To improve the accuracy of photometric redshift estimation for CSST, we calibrated the CWW+KIN templates using a perturbation algorithm with broadband photometric data from the CSST mock catalog. This calibration used a training set consisting of approximately 4,500 galaxies, which is 10% of the total galaxy sample. The outlier fraction and scatter of the photometric redshifts derived from the calibrated templates are 2.55% and 0.036, respectively. Compared to the CWW+KIN templates, these values are reduced by 34% and 23%, respectively. This demonstrates that SED templates calibrated with a small training set can effectively optimize photometric redshift accuracy for future large-scale surveys like CSST, especially with limited spectral training data.

astro-ph.CO↗

arXiv2024

Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning

In Few-Shot Learning (FSL), traditional metric-based approaches often rely on global metrics to compute similarity. However, in natural scenes, the spatial arrangement of key instances is often inconsistent across images. This spatial misalignment can result in mismatched semantic pixels, leading to inaccurate similarity measurements. To address this issue, we propose a novel method called the Layer-Wise Features Metric of Semantic-Pixel Matching (LWFM-SPM) to make finer comparisons. Our method enhances model performance through two key modules: (1) the Layer-Wise Embedding (LWE) Module, which refines the cross-correlation of image pairs to generate well-focused feature maps for each layer; (2)the Semantic-Pixel Matching (SPM) Module, which aligns critical pixels based on semantic embeddings using an assignment algorithm. We conducted extensive experiments to evaluate our method on four widely used few-shot classification benchmarks: miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS. The results indicate that LWFM-SPM achieves competitive performance across these benchmarks. Our code will be publicly available on https://github.com/Halo2Tang/Code-for-LWFM-SPM.

cs.CV↗

arXiv2024

Photometric Redshift Estimation for CSST Survey with LSTM Neural Networks

Accurate estimation of photometric redshifts (photo-$z$s) is crucial for cosmological surveys. Various methods have been developed for this purpose, such as template fitting methods and machine learning techniques, each with its own applications, advantages, and limitations. In this study, we propose a new approach that utilizes a deep learning model based on Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) to predict photo-$z$. Unlike many existing machine learning models, our method requires only flux measurements from different observed filters as input. The model can automatically learn the complex relationships between the flux data across different wavelengths, eliminating the need for manually extracted or derived input features, thereby providing precise photo-$z$ estimates. The effectiveness of our proposed model is evaluated using simulated data from the Chinese Space Station Telescope (CSST) sourced from the Hubble Space Telescope Advanced Camera for Surveys (HST-ACS) and the COSMOS catalog, considering anticipated instrument effects of the future CSST. Results from experiments demonstrate that our LSTM model, compared to commonly used template fitting and machine learning approaches, requires minimal input parameters and achieves high precision in photo-$z$ estimation. For instance, when trained on the same dataset and provided only with photometric fluxes as input features, the proposed LSTM model yields one-third of the outliers $f_{out}$ observed with a Multi-Layer Perceptron Neural Network (MLP) model, while the normalized median absolute deviation $\rm \sigma_{NMAD}$ is only two-thirds that of the MLP model. This study presents a novel approach to accurately estimate photo-$z$s of galaxies using photometric data from large-scale survey projects.

astro-ph.GA↗

arXiv2024

Mutual Information calculation on different appearances

Mutual information has many applications in image alignment and matching, mainly due to its ability to measure the statistical dependence between two images, even if the two images are from different modalities (e.g., CT and MRI). It considers not only the pixel intensities of the images but also the spatial relationships between the pixels. In this project, we apply the mutual information formula to image matching, where image A is the moving object and image B is the target object and calculate the mutual information between them to evaluate the similarity between the images. For comparison, we also used entropy and information-gain methods to test the dependency of the images. We also investigated the effect of different environments on the mutual information of the same image and used experiments and plots to demonstrate.

cs.CV↗

arXiv2024

Imputation of Missing Photometric Data and Photometric Redshift Estimation for CSST

Accurate photometric redshift (photo-$z$) estimation requires support from multi-band observational data. However, in the actual process of astronomical observations and data processing, some sources may have missing observational data in certain bands for various reasons. This could greatly affect the accuracy and reliability of photo-$z$ estimation for these sources, and even render some estimation methods unusable. The same situation may exist for the upcoming Chinese Space Station Telescope (CSST). In this study, we employ a deep learning method called Generative Adversarial Imputation Networks (GAIN) to impute the missing photometric data in CSST, aiming to reduce the impact of data missing on photo-$z$ estimation and improve estimation accuracy. Our results demonstrate that using the GAIN technique can effectively fill in the missing photometric data in CSST. Particularly, when the data missing rate is below 30\%, the imputation of photometric data exhibits high accuracy, with higher accuracy in the $g$, $r$, $i$, $z$, and $y$ bands compared to the $NUV$ and $u$ bands. After filling in the missing values, the quality of photo-$z$ estimation obtained by the widely used Easy and Accurate Zphot from Yale (EAZY) software is notably enhanced. Evaluation metrics for assessing the quality of photo-$z$ estimation, including the catastrophic outlier fraction ($f_{out}$), the normalized median absolute deviation ($\rm {\sigma_{NMAD}}$), and the bias of photometric redshift ($bias$), all show some degree of improvement. Our research will help maximize the utilization of observational data and provide a new method for handling sample missing values for applications that require complete photometry data to produce results.

astro-ph.IM↗

arXiv2024

Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation

Image segmentation holds a vital position in the realms of diagnosis and treatment within the medical domain. Traditional convolutional neural networks (CNNs) and Transformer models have made significant advancements in this realm, but they still encounter challenges because of limited receptive field or high computing complexity. Recently, State Space Models (SSMs), particularly Mamba and its variants, have demonstrated notable performance in the field of vision. However, their feature extraction methods may not be sufficiently effective and retain some redundant structures, leaving room for parameter reduction. Motivated by previous spatial and channel attention methods, we propose Triplet Mamba-UNet. The method leverages residual VSS Blocks to extract intensive contextual features, while Triplet SSM is employed to fuse features across spatial and channel dimensions. We conducted experiments on ISIC17, ISIC18, CVC-300, CVC-ClinicDB, Kvasir-SEG, CVC-ColonDB, and Kvasir-Instrument datasets, demonstrating the superior segmentation performance of our proposed TM-UNet. Additionally, compared to the previous VM-UNet, our model achieves a one-third reduction in parameters.

eess.IV↗

arXiv2023

Estimating Photometric Redshift from Mock Flux for CSST Survey by using Weighted Random Forest

Accurate estimation of photometric redshifts (photo-$z$) is crucial in studies of both galaxy evolution and cosmology using current and future large sky surveys. In this study, we employ Random Forest (RF), a machine learning algorithm, to estimate photo-$z$ and investigate the systematic uncertainties affecting the results. Using galaxy flux and color as input features, we construct a mapping between input features and redshift by using a training set of simulated data, generated from the Hubble Space Telescope Advanced Camera for Surveys (HST-ACS) and COSMOS catalogue, with the expected instrumental effects of the planned China Space Station Telescope (CSST). To improve the accuracy and confidence of predictions, we incorporate inverse variance weighting and perturb the catalog using input feature errors. Our results show that weighted RF can achieve a photo-$z$ accuracy of $\rm \sigma_{NMAD}=0.025$ and an outlier fraction of $\rm \eta=2.045\%$, significantly better than the values of $\rm \sigma_{NMAD}=0.043$ and $\rm \eta=6.45\%$ obtained by the widely used Easy and Accurate Zphot from Yale (EAZY) software which uses template-fitting method. Furthermore, we have calculated the importance of each input feature for different redshift ranges and found that the most important input features reflect the approximate position of the break features in galaxy spectra, demonstrating the algorithm's ability to extract physical information from data. Additionally, we have established confidence indices and error bars for each prediction value based on the shape of the redshift probability distribution function, suggesting that screening sources with high confidence can further reduce the outlier fraction.

astro-ph.CO↗