In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at https://github.com/UnicomAI/ShortDF.

Text-to-SQL is an innovative tool that automatically converts natural language queries into structured SQL statements, enabling users to extract data from complex databases efficiently. Automatic correction techniques are employed to enhance the performance of Text-To-SQL models. However, these corrections encounter challenges stemming from a lack of critical information in input sequences, substantial noise, and insufficient contextual knowledge, all hindering optimal parser performance. We propose a correction method based on correlation degree and multi-round error evaluation (CMC) to address these issues. Our approach uses a correlation evaluator to eliminate redundant table columns, emphasize key aspects of the input sequence, and minimize unnecessary noise. The multi-round error evaluator integrates database execution analysis of SQL queries, allowing for the updating of erroneous information and background knowledge to better guide model correction. Experimental results indicate that our method achieves a 3.3% increase in exact set execution accuracy (EX) and a 2.0% increase in exact match accuracy (EM) on the Spider benchmark, surpassing current mainstream automatic correction methods. Additionally, our correction technique has significantly improved the performance of the Text-To-SQL baseline model.

Convolution neural network is successful in pervasive vision tasks, including label distribution learning, which usually takes the form of learning an injection from the nonlinear visual features to the well-defined labels. However, how the discrepancy between features is mapped to the label discrepancy is ambient, and its correctness is not guaranteed. To address these problems, we study the mathematical connection between feature and its label, presenting a general and simple framework for label distribution learning. We propose a so-called Triangular Distribution Transform (TDT) to build an injective function between feature and label, guaranteeing that any symmetric feature discrepancy linearly reflects the difference between labels. The proposed TDT can be used as a plug-in in mainstream backbone networks to address different label distribution learning tasks. Experiments on Facial Age Recognition, Illumination Chromaticity Estimation, and Aesthetics assessment show that TDT achieves on-par or better results than the prior arts. Code is available at https://github.com/redcping/TDT.

The relationship between various objects in real life is very important and universal. However, existing object detection models, especially Two-stage models, mostly rely solely on instance learning of individual objects, which use limited global information to extract regions of interest and neglect the correlation between object instances. Therefore, this article proposes an Object Correlation Matrix (OCM) for measuring the correlation between objects, obtained by statistical analysis of instance information in the MS COCO dataset. Based on OCM, we design a Secondary Scoring Module (SSM) that combines the confidence and correlation of surrounding objects to correct the predicted outputs of the original network. Then apply the SSM to the post-processing stage, which is entirely independent of the original network and does not require adding any parameters or retraining the original network. Hence, this module is easy to embed in object detection networks and has achieved performance improvement.

Camouflaged object detection (COD) aims to accurately recognize targets in intricate environments that blend into the background. Although numerous camouflage object identification techniques have demonstrated effectiveness, they often possess a substantial number of parameters. Therefore, we propose a new lightweight edge-guided multilevel feature fusion camouflaged object detection network, codenamed as LEMFNet. Initially, we adopt a lightweight CNN network model for feature extraction to reduce model complexity. Subsequently, we introduced a neighborhood feature association module (NFAM) to integrate feature information from different stages to obtain complementary feature representations and enhance the overall model performance. Furthermore, to obtain a more complete object structure, we introduce a boundary aggregation module (BAM) to delve into the edge semantics associated with the target and integrate the edge features into the proposed edge-guided aggregation module (EGAM). Experiments on three challenging benchmarks demonstrate our approach, with fewer parameters, achieves comparable or superior performance, effectively balancing resource utilization and accuracy.

The characterization of shale pore size, surface area, porosity, fractal dimension, and other parameters is crucial for estimating shale gas reserves. Scanning electron microscope (SEM) images of shale provide comprehensive information on organic pores, inorganic pores, and micro-fractures within the rock. However, there are limited intelligent segmentation methods available for shale SEM images. To address this gap, we introduce a multi-axis frequency domain residual semantic segmentation network, referred to as MaFR2UNet. This network refines the feature extraction process within each of the four multi-scale branches of the Res2Net architecture. It incorporates a frequency-domain-leveraging multi-axis frequency domain residual block (MaFR) to enhance the network’s feature extraction capabilities. This design enables the model to effectively capture texture and detailed features within the image. Experimental results on a shale SEM image dataset demonstrate the superior segmentation performance of the refined algorithm.

Multi-label text classification (MLTC) is an important task in the field of natural language processing (NLP). Suffering from limited input length, most existing models learn text representation and label representation separately, leading to the overlook of correlations between texts and labels. To this end, we introduce a comprehensive model for the MLTC task. Under the same representation space, our model, which is equipped with Graph Convolutional Network (GCN) layer, attention mechanism, and contrastive learning objective, learns representations of texts and labels jointly. To tackle the issue caused by the input length limitation, we develop a two-stage label reduction method via the application of label merging and association. Our method’s effectiveness is validated through extensive experiments on various MLTC datasets, unraveling the intricate correlations between texts and labels.

Naked eye recognition of age is usually based on comparison with the age of others. However, this idea is ignored by computer tasks because it is difficult to obtain representative contrast images of each age. Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation. We let the input of transfer learning as the binary code of age natural number to obtain continuous age feature information. The learned two groups of values in Binary code mapping are corresponding to the mean and standard deviation of the comparison ages. In summary, our method consists of four parts: FaceEncoder, DAA operation, Binary code mapping, and AgeDecoder modules. After getting the delta age via AgeDecoder, we take the average value of all comparison ages and delta ages as the predicted age. Compared with state-of-the-art methods, our method achieves better performance with fewer parameters on multiple facial age datasets. Code is available at https://github.com/redcping/Delta_Age_AdaIN

Residuals and inception are two commonly used module that makes the network deeper and wider to achieve better performance. And the combination of these two modules which is usually referred to as inception-resnet can get a better result. In this paper, we propose a new type of combination to give full play to the role of residuals and inception, making network learning more abundant features. The new proposed module is called Residual Inception (RI) which enjoys the same width as the inception module in GoogLeNet. In RI, each parallel cascade structure is replaced by a densely block or a modified residual block for gaining a better performance and a lower computational cost. Finally, we evaluate our proposed network on three highly competitive datasets and the results demonstrate its superiority in comparison with the state-of-the-art.