Defect detection in multimedia data plays a pivotal role in industrial manufacturing. However, existing methods are primarily designed for closed-world scenarios and can only identify defect classes in the training data, limiting their ability to effectively detect unknown class defects that arise during production. To address this critical limitation, we propose a novel approach by introducing industrial defect open set recognition (IDOSR), which overcomes the challenge of recognizing unknown defect classes. Furthermore, to tackle the issues of limited training samples and subtle inter-class differences in IDOSR, we present a high-frequency feature enhancement open set recognition (HFFE-OSR) method. Specifically, HFFE-OSR employs a high-frequency structural feature fusion enhancement strategy to meticulously extract and fuse defect-related high-frequency structural features. This enables the network to comprehensively learn defect target representations even under limited training samples, resulting in robust feature extraction for known classes, thereby improving the discriminability between known and unknown classes and addressing the difficulty of distinguishing between them. Additionally, a class mutual information constraint strategy is introduced to measure and reduce the mutual information among defect features from different classes. This ensures the independence of defect features across known classes, further enhancing their discriminability and significantly improving recognition performance for known classes. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art OSR methods on ID-OSD and MVTec datasets, achieving improvements of at least 7% in accuracy (ACC), 22% in F1 score, and 10% in AUROC, highlighting the effectiveness of our approach in industrial defect detection.

Dense pixel-wise labeling of large-scale remote sensing images (RSI) is very time-consuming, while sparse labels (i.e., points, scribbles, or blocks) can be an efficient way to reduce labeling costs. Most existing sparse label-based methods adopt only one type of label for image segmentation, which cannot reflect the complex land covers in the RSI for training the model, thus leading to inferior segmentation performance. We observe that land covers with different shapes and complexity can be optimally represented by different sparse labels. Inspired by this observation, we propose a novel sparse labeling framework, termed Hybrid Sparse Labeling (HSLabeling), for large-scale RSI segmentation. Our HSLabeling can adaptively select the optimal hybrid sparse labels for different land covers, according to labeling cost and segmentation contribution of different sparse labels. Specifically, we first propose a label segmentation contribution information estimation module that estimates the information of different sparse labels according to the diversity and shape of land covers. After that, we propose an Optimal Hybrid Labeling Strategy (OHLS) to assign optimal types of labels for different land covers. In the OHLS, label assignment is formulated as an optimization problem that trades off label segmentation contribution information and labeling cost. We employ the greedy algorithm to efficiently solve the optimization problem and adaptively assign labels for varied land covers. Extensive experiments on three large-scale RSI datasets have demonstrated that our HSLabeling achieves almost fully supervised performance with extremely low labeling costs. In addition, compared with the single type sparse label, HSLabeling can also utilize much lower labeling costs to obtain the same performance. The source code is available at https://github.com/linjiaxing99/HSLabeling.

The small scale and weak intensity of infrared (IR) small targets result in extremely sparse target features, making small target detection in complex environments extremely susceptible to strong background noise interference. Most existing detection methods only focus on sparse feature extraction of targets, while ignoring the problem of strong background clutter interference, which leads to significant limitations in detection performance in complex scenes. Therefore, to address this issue, we propose a new IR small target detection network based on high- and low-frequency semantic reconstruction, namely the HLSR-net. In the HLSR-net, we draw inspiration from the frequency characteristics differences between targets and backgrounds in IR images, and use the proposed high- and low-frequency semantic reconstruction strategy to suppress background clutter interference, effectively extracting sparse features of targets. First, in the latent feature space of the input image, high-frequency target and low-frequency background features are extracted separately through fast Fourier frequency transformation. Second, by utilizing the difference in frequency characteristics between small targets and background clutter, target enhancement and background suppression are respectively carried out through the designed high- and low-frequency reconstruction networks. Finally, to further enrich the feature expression of the target, we designed a fusion output strategy to achieve detection of small targets. Sufficient experimental results indicate that the proposed HLSR-net achieves the performance of SOTA on the benchmark dataset, with an accuracy improvement of 6%.

The success of deep learning methods heavily relies on the availability of adequate samples. However, in the task of infrared small target detection (ISTD), the lack of high-quality training samples is a challenging problem due to the confidentiality of the application field and the difficulty of labeling. This limitation often leads to suboptimal detection performance of convolutional neural networks (CNNs). To address this challenge, we propose an adaptive labeling strategy and an ISTD network called the multi-criteria decision network (MCDNet) to achieve higher-quality sample labeling and more accurate detection results. In the adaptive labeling strategy, we propose a second-order differential autocorrelation method to determine the size of fuzzy edge targets accurately. In addition, we introduce local backgrounds to enhance the saliency information in the labels and improve the richness and contrast of training label content. To obtain accurate and robust detection results with limited target feature information, we design MCDNet. In particular, we propose a multi-criteria decision method that can combine the CNN decisions and the infrared small target prior saliency decisions through weighted fusion, and set decision weights based on the importance of different decision criteria in the decision-making process. This method can integrate the advantages of both the CNN decisions and the prior saliency decisions, avoid the one-sidedness of a single criterion, and improve the reliability and stability of the decision-making. The experimental results indicate that our method has a higher accuracy compared to other contrastive methods.

To solve the problems of slow detection speed and poor robustness of existing infrared (IR) small target detection methods in complex environments, a lightweight detection model MiniIR-net is proposed in this letter. In the MiniIR-net model, to reduce the number of parameters required for model fitting, a multiscale target context feature extraction (TCVE) module is proposed to enrich the feature expression of the target. In addition, to improve the feature mapping capability of MiniIR-net, a feature mapping upsampling network by fusing the deep and shallow features is designed. In the process of feature mapping upsampling, the network uses target features with different depths to make up for the loss of target features caused by pooling. It is proven by the experiment that the proposed MiniIR-net network is superior to the existing detection methods in detection speed, accuracy and robustness in a complex environment. The model size of MiniIR-net is at least 1/260 of the current detection model, and the detection accuracy is improved by at least 5%. The source code of this article can be obtained athttps://github.com/yangzhen1252/MiniIR-net.

Intractable sparse feature extraction, over-weight model size, and limited training samples are currently bewildering in infrared dim small target detection, which are not adequately addressed by current state-of-the-art (SOTA) methods. Here, to synchronously address these issues, a dense multi-level feature extraction and fusion network (DMEF-net) is designed, mainly consisting of two modules: target context and Gaussian saliency feature extraction module (TCGS) and multi-level dense feature fusion structure (MLDF). Inspired by the physical thermal diffusion model and the human visual mechanism for small-scale targets, Gaussian salience features and local context features are introduced into the target feature expression through the designed TCGS module to solve the sparse feature extraction problem. Then, to solve the over-weight model size problem, a novel MLDF module is designed to incorporate the feature reuse mechanism into our model, thereby significantly reducing the number of trainable parameters. Finally, in the training procedure, an efficient saliency labeling strategy is proposed to jointly supervise the model training in both Euclidean and Gaussian spaces, ultimately enhancing the model’s ability to explore the target features and alleviate performance deterioration when the training samples are limited. Extensive experiments on several large-scale open datasets, including TDSATUA and MTDUCB, prove that the proposed DMEF-net outperforms other SOTA methods by 8% in accuracy and has 4800% less model size.

Infrared (IR) small target detection in a complex environment has become a hot topic. Due to the dim intensity and small scale of the target and the strong background clutter, the existing algorithms cannot achieve satisfactory results, namely poor detection performance and poor real-time performance. In this letter, a new real-time small target detection algorithm based on smoothness measure and thermal diffusion (STD) is proposed. First, the smoothness measure is proposed to extract smoothness features of small targets and suppress the clutter background. Then, we improve the existing thermal diffusion equation and design a thermal diffusion operator to extract the target’s thermal diffusion feature. The operator will further enhance the small and dim target’s energy. Finally, the fusion result image—in which the background is suppressed and the target is enhanced—is acquired after combining smoothness and thermal diffusion flowmetry. The experimental results demonstrate that the detection speed of the proposed algorithm is at least four times faster than that of existing algorithms under the same detection conditions. In addition, the proposed algorithm can achieve outstanding detection performance for IR images with different types of complex backgrounds and targets’ sizes within$7\times7$.

In the complex background, the contrast and signal-to-noise (SNR) ratio of the infrared (IR) small target are low. Therefore, the traditional IR small target detection algorithms are difficult to achieve good detection performance when the characteristics of small targets are sparse. To solve this problem, an IR small target detection network with generate label and feature mapping (GLFM)-net is proposed in this letter. First, in the GLFM-net model, a scale adaptive feature extraction network is proposed for the IR small target sparse features extraction, and then, the multilayer joint upsampling feature mapping network is proposed for small target feature mapping and background suppression. Based on this model, the feature mapping results of IR dim and small targets with the greatly suppressed background are obtained. Second, in model training, we designed a 2-D Gaussian label generation strategy for the problem of sample imbalance, which can achieve excellent detection performance by using small training samples. The experimental results show that the network can detect IR small targets with different sizes and low SNRs in various complex backgrounds and has good effectiveness and robustness compared with the existing algorithms.

Aiming at the problems of large parameters and low detection speed of the existing remote sensing road detection network model, a lightweight remote sensing road detection network (LRSR-net) model is proposed in this paper. In the feature encoding stage of LRSR-net, an efficient road target feature extraction module dilated joint convolution module is proposed. This module can eliminate the feature loss caused by the pooling layer, so that the network model can use a small amount of parameters to learn the characteristics of road targets. In addition, in the feature decoding stage, to eliminate the damage of the target data structure caused by the upsampling operation, a joint decoding module is proposed. The joint decoding module can effectively map the characteristics of road targets and suppress the background clutter. The systematic experimental results have demonstrated that the proposed lightweight road target detection model has excellent detection performance under the condition of small model parameters, and most performance indexes are better than those of the existing advanced detection methods. The source code of this article can be obtained from https://github.com/yangzhen1252/IRSR-net.