arXiv subjects

Chenghong Zhang

Publications and source records attributed to Chenghong Zhang.

6 recordsLinked to original sources

arXiv2026

Bridging mid and near infrared by combining optomechanics and self mixing

This work describes a self-mixing-assisted optomechanical platform for transferring information between near- and mid-infrared radiation. In particular, the self-mixing signal of a mid-infrared quantum cascade laser is used to detect the oscillation of a membrane driven by light-induced forces exerted by a near-infrared excitation beam, which is amplitude-modulated at the membrane resonance frequency. This technique benefits from spectral broadness and, therefore, can link different spectral regions from both the excitation and probe sides. This versatility can pave the way for future applications of this self-mixing-assisted optomechanical platform in communication and advanced sensing systems.

physics.optics↗

arXiv2026

Sub-doppler trace-gas photoacoustic spectroscopy

Molecules are emerging as new benchmark for metrology and fundamental physics research, driving the demand for spectroscopic techniques combining high sensitivity and resolution. Photoacoustic spectroscopy has proven to combine high sensitivity with appealing features like compactness, wavelength-independent and background-free detection. To date, photoacoustic sensing has mostly been focused on high-pressure applied trace-gas analysis, while accessing the low-pressure regime has been considered not compatible with efficient acoustic wave propagation. However, sensing gas samples at low pressure is the key to get access to high-resolution spectroscopy. Here, we demonstrate that sub-Doppler saturation spectroscopy can be performed on low-pressure trace gases in a cavity-enhanced photoacoustic sensor with mW-level mid-infrared radiation. Moreover, we show that the same setup can be operated at higher pressure, enabling trace-gas detection with 5 parts-per-billion sensitivity with a laser power as low as 35 microwatts. This allows to extend the unique advantages of the photoacoustic technique to metrology and fundamental physics and provides the mid-infrared with a cost-effective, flexible tool combining high sensitivity and resolution.

physics.optics↗

arXiv2025

Monocular Depth Guided Occlusion-Aware Disparity Refinement via Semi-supervised Learning in Laparoscopic Images

Occlusion and the scarcity of labeled surgical data are significant challenges in disparity estimation for stereo laparoscopic images. To address these issues, this study proposes a Depth Guided Occlusion-Aware Disparity Refinement Network (DGORNet), which refines disparity maps by leveraging monocular depth information unaffected by occlusion. A Position Embedding (PE) module is introduced to provide explicit spatial context, enhancing the network's ability to localize and refine features. Furthermore, we introduce an Optical Flow Difference Loss (OFDLoss) for unlabeled data, leveraging temporal continuity across video frames to improve robustness in dynamic surgical scenes. Experiments on the SCARED dataset demonstrate that DGORNet outperforms state-of-the-art methods in terms of End-Point Error (EPE) and Root Mean Squared Error (RMSE), particularly in occlusion and texture-less regions. Ablation studies confirm the contributions of the Position Embedding and Optical Flow Difference Loss, highlighting their roles in improving spatial and temporal consistency. These results underscore DGORNet's effectiveness in enhancing disparity estimation for laparoscopic surgery, offering a practical solution to challenges in disparity estimation and data limitations.

cs.CV↗

arXiv2024

EWMoE: An effective model for global weather forecasting with mixture-of-experts

Weather forecasting is a crucial task for meteorologic research, with direct social and economic impacts. Recently, data-driven weather forecasting models based on deep learning have shown great potential, achieving superior performance compared with traditional numerical weather prediction methods. However, these models often require massive training data and computational resources. In this paper, we propose EWMoE, an effective model for accurate global weather forecasting, which requires significantly less training data and computational resources. Our model incorporates three key components to enhance prediction accuracy: 3D absolute position embedding, a core Mixture-of-Experts (MoE) layer, and two specific loss functions. We conduct our evaluation on the ERA5 dataset using only two years of training data. Extensive experiments demonstrate that EWMoE outperforms current models such as FourCastNet and ClimaX at all forecast time, achieving competitive performance compared with the state-of-the-art models Pangu-Weather and GraphCast in evaluation metrics such as Anomaly Correlation Coefficient (ACC) and Root Mean Square Error (RMSE). Additionally, ablation studies indicate that applying the MoE architecture to weather forecasting offers significant advantages in improving accuracy and resource efficiency. Code is available at https://github.com/Tomoyi/EWMoE.

physics.ao-ph↗

arXiv2023

W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting

Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods, making it highly suitable for deep learning models. In this paper, we apply pre-training techniques to weather forecasting and propose W-MAE, a Weather model with Masked AutoEncoder pre-training for weather forecasting. W-MAE is pre-trained in a self-supervised manner to reconstruct spatial correlations within meteorological variables. On the temporal scale, we fine-tune the pre-trained W-MAE to predict the future states of meteorological variables, thereby modeling the temporal dependencies present in weather data. We conduct our experiments using the fifth-generation ECMWF Reanalysis (ERA5) data, with samples selected every six hours. Experimental results show that our W-MAE framework offers three key benefits: 1) when predicting the future state of meteorological variables, the utilization of our pre-trained W-MAE can effectively alleviate the problem of cumulative errors in prediction, maintaining stable performance in the short-to-medium term; 2) when predicting diagnostic variables (e.g., total precipitation), our model exhibits significant performance advantages over FourCastNet; 3) Our task-agnostic pre-training schema can be easily integrated with various task-specific models. When our pre-training framework is applied to FourCastNet, it yields an average 20% performance improvement in Anomaly Correlation Coefficient (ACC).

cs.LG↗

arXiv2023

I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding

Spoken language understanding (SLU) typically includes two subtasks: intent detection and slot filling. Currently, it has achieved great success in high-resource languages, but it still remains challenging in low-resource languages due to the scarcity of labeled training data. Hence, there is a growing interest in zero-shot cross-lingual SLU. Despite of the success of existing zero-shot cross-lingual SLU models, most of them neglect to achieve the mutual guidance between intent and slots. To address this issue, we propose an Intra-Inter Knowledge Distillation framework for zero-shot cross-lingual Spoken Language Understanding (I$^2$KD-SLU) to model the mutual guidance. Specifically, we not only apply intra-knowledge distillation between intent predictions or slot predictions of the same utterance in different languages, but also apply inter-knowledge distillation between intent predictions and slot predictions of the same utterance. Our experimental results demonstrate that our proposed framework significantly improves the performance compared with the strong baselines and achieves the new state-of-the-art performance on the MultiATIS++ dataset, obtaining a significant improvement over the previous best model in overall accuracy.

cs.CL↗