arXiv subjects

Jonathan Wu

Publications and source records attributed to Jonathan Wu.

8 recordsLinked to original sources

arXiv2026

Spectral-Morphological Attention U-Net: An Efficient Network for Active Wildfire Detection

Over the past decades, the frequency of global wildfires has been increasing steadily. Therefore, if the fire can be detected and precisely located at an early stage, the potential hazards caused by it can be minimized to the greatest extent. The machine learning methods based on satellite images, due to their ability to automatically monitor extremely remote and vast areas, have shown great potential for application in the field of wildfire detection. To address this challenge, we proposed a new model named spectral-morphological attention U-Net(SMA-UNet), which includes a spectral attention module, a residual attention UNet backbone, a channel-spatial modulator, and a pair of differentiable morphological gates. We trained and evaluated this model with two datasets. These modules, excluding the backbone, are used to detect active fire events for the first time, especially the pair of differentiable morphological gates, which is innovatively developed. The proposed model achieved the highest scores in both datasets (e.g., intersection over union 75.16% in TS-SatFire, 22.50% in Sen2Fire). By conducting ablation studies of each module, we compared their independent contributions and tested their combinations. Ultimately, the integration of these modules yields a highly robust framework that significantly improves segmentation consistency across diverse and complex environmental conditions. Future work will focus on validating the proposed architecture across large-scale, multi-regional datasets from different satellite sensors to establish its broader generalizability for global wildfire detection.

cs.CV↗

arXiv2026

Decoupling Vision and Language: Codebook Anchored Visual Adaptation

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or fine-grained classification, where representation errors can cascade through the language model, leading to incorrect responses. Existing adaptation methods modify the continuous feature interface between encoder and language model through projector tuning or other parameter-efficient updates, which still couples the two components and requires re-alignment whenever the encoder changes. We introduce CRAFT (Codebook RegulAted Fine-Tuning), a lightweight method that fine-tunes the encoder using a discrete codebook that anchors visual representations to a stable token space, achieving domain adaptation without modifying other parts of the model. This decoupled design allows the adapted encoder to seamlessly boost the performance of LVLMs with different language architectures, as long as they share the same codebook. Empirically, CRAFT achieves an average gain of 13.51% across 10 domain-specific benchmarks such as VQARAD and PlantVillage, while preserving the LLM's linguistic capabilities and outperforming peer methods that operate on continuous tokens.

cs.CV↗

arXiv2025

A Review of Neural Networks in Precipitation Prediction

Precipitation prediction has undergone a profound transformation. A notable limitation of traditional NWP is the need for extensive statistical post-processing. To address this challenge, neural network-based approaches were developed. These approaches offer a framework that directly learns the mapping from atmospheric predictors to precipitation targets. Based on the technological development, this article first reviews the traditional precipitation forecasting methods and summarizes the development trends of precipitation forecasting based on neural networks. We then outline the training process, loss functions, and some datasets for precipitation prediction. In the main body of the article, we detail the basic artificial neural networks (ANNs), spatial feature extraction models, time feature extraction models, generative models, Transformer models, graph neural networks (GNNs), and emerging hybrid models. Finally, in the appendix, we supplement the commonly used evaluation metrics. This paper focuses on the advantages and disadvantages of various neural network models in precipitation forecasting applications, and also pays attention to the latest progress of neural network-based methods. Overall, neural networks have significantly improved the accuracy of short-term and medium-term precipitation forecasting, but still face challenges in representing extreme rainfall, handling imbalanced data, and ensuring physical consistency. The latest progress shows that future prediction systems will increasingly rely on the integration of multiple sources of data and hybrid physical-data-driven models to enhance their robustness and applicability. By compositing research covering multiple eras and paradigms, we not only depict the history of neural networks in precipitation prediction but also outline future directions in next generation forecasting systems.

cs.LG↗

arXiv2021

Deconvolution-and-convolution Networks

2D Convolutional neural network (CNN) has arguably become the de facto standard for computer vision tasks. Recent findings, however, suggest that CNN may not be the best option for 1D pattern recognition, especially for datasets with over 1 M training samples, e.g., existing CNN-based methods for 1D signals are highly reliant on human pre-processing. Common practices include utilizing discrete Fourier transform (DFT) to reconstruct 1D signal into 2D array. To add to extant knowledge, in this paper, a novel 1D data processing algorithm is proposed for 1D big data analysis through learning a deep deconvolutional-convolutional network. Rather than resorting to human-based techniques, we employed deconvolution layers to convert 1 D signals into 2D data. On top of the deconvolution model, the data was identified by a 2D CNN. Compared with the existing 1D signal processing algorithms, DCNet boasts the advantages of less human-made inference and higher generalization performance. Our experimental results from a varying number of training patterns (50 K to 11 M) from classification and regression demonstrate the desirability of our new approach.

cs.CV↗

arXiv2020

L2-Constrained RemNet for Camera Model Identification and Image Manipulation Detection

Source camera model identification (CMI) and image manipulation detection are of paramount importance in image forensics. In this paper, we propose an L2-constrained Remnant Convolutional Neural Network (L2-constrained RemNet) for performing these two crucial tasks. The proposed network architecture consists of a dynamic preprocessor block and a classification block. An L2 loss is applied to the output of the preprocessor block, and categorical crossentropy loss is calculated based on the output of the classification block. The whole network is trained in an end-to-end manner by minimizing the total loss, which is a combination of the L2 loss and the categorical crossentropy loss. Aided by the L2 loss, the data-adaptive preprocessor learns to suppress the unnecessary image contents and assists the classification block in extracting robust image forensics features. We train and test the network on the Dresden database and achieve an overall accuracy of 98.15%, where all the test images are from devices and scenes not used during training to replicate practical applications. The network also outperforms other state-of-the-art CNNs even when the images are manipulated. Furthermore, we attain an overall accuracy of 99.68% in image manipulation detection, which implies that it can be used as a general-purpose network for image forensic tasks.

eess.IV↗

arXiv2020

Deep Networks with Fast Retraining

Recent work [1] has utilized Moore-Penrose (MP) inverse in deep convolutional neural network (DCNN) learning, which achieves better generalization performance over the DCNN with a stochastic gradient descent (SGD) pipeline. However, Yang's work has not gained much popularity in practice due to its high sensitivity of hyper-parameters and stringent demands of computational resources. To enhance its applicability, this paper proposes a novel MP inverse-based fast retraining strategy. In each training epoch, a random learning strategy that controls the number of convolutional layers trained in the backward pass is first utilized. Then, an MP inverse-based batch-by-batch learning strategy, which enables the network to be implemented without access to industrial-scale computational resources, is developed to refine the dense layer parameters. Experimental results empirically demonstrate that fast retraining is a unified strategy that can be used for all DCNNs. Compared to other learning strategies, the proposed learning pipeline has robustness against the hyper-parameters, and the requirement of computational resources is significantly reduced. [1] Y. Yang, J. Wu, X. Feng, and A. Thangarajah, "Recomputation of dense layers for the perfor-238mance improvement of dcnn," IEEE Trans. Pattern Anal. Mach. Intell., 2019.

cs.LG↗

arXiv2018

Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet

The performance of a computer-aided automated diagnosis system of lung cancer from Computed Tomography (CT) volumetric images greatly depends on the accurate detection and segmentation of tumor regions. In this paper, we present Recurrent 3D-DenseUNet, a novel deep learning based architecture for volumetric lung tumor segmentation from CT scans. The proposed architecture consists of a 3D encoder block that learns to extract fine-grained spatial and coarse-grained temporal features, a recurrent block of multiple Convolutional Long Short-Term Memory (ConvLSTM) layers to extract fine-grained spatio-temporal information, and finally a 3D decoder block to reconstruct the desired volume segmentation masks from the latent feature space. The encoder and decoder blocks consist of several 3D-convolutional layers that are densely connected among themselves so that necessary feature aggregation can occur throughout the network. During prediction, we apply selective thresholding followed by morphological operation, on top of the network prediction, to better differentiate between tumorous and non-tumorous image-slices, which shows more promise than only thresholding-based approaches. We train and test our network on the NSCLC-Radiomics dataset of 300 patients, provided by The Cancer Imaging Archive (TCIA) for the 2018 IEEE VIP Cup. Moreover, we perform an extensive ablation study of different loss functions in practice for this task. The proposed network outperforms other state-of-the-art 3D segmentation architectures with an average dice score of 0.7228.

eess.IV↗

arXiv2016

Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions

Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 x 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled filter-sharing network that leverages high resolution (HR) videos during training in order to assist an eLR ConvNet. We also study methods for fusing spatial and temporal ConvNets customized for eLR videos in order to take advantage of appearance and motion information. Our method outperforms state-of-the-art methods at extremely low resolutions on IXMAS (93.7%) and HMDB (29.2%) datasets.

cs.CV↗