Search

The unavailability and variability of training samples are the two essential concerns in the training of deep neural network models for image classification. For automated image monitoring systems, these problems are difficult when training a model through supervised learning methods because of the time and effort required. This paper proposes an adaptive solution to this problem by applying online semi-supervised learning to an automated insect pest monitoring system. The method used includes unsupervised pseudo-labelling of insect images and the training of semi-supervised classifier models for insect image recognition. The pseudo-labelling algorithm includes three major components: image labelling, label reconfirmation, and sample cleaning. Experiments were conducted on two unlabelled 1-year insect image datasets to evaluate the efficacy of the proposed method. It was found that the pseudo-labelling algorithm could achieve accuracy up to 0.963, hence enabling automated training data collection. The temporal improvement of the insect recognition performance by including new training data to retrain the classifier model was comparable in performance to the supervised learning approach as evaluated by cluster density, silhouette score, and F 1 -score. The proposed method was also able to automatically collect quality samples and train models regardless of the complexity of the images, making it a good alternative to replace laborious supervised learning. The proposed method can prevent contamination of a training dataset when images from new locations are collected. The presented techniques may also be used in other continuous learning applications that require automated training data collection and online model update. [Display omitted] • Semi-supervised learning method for an insect pest monitoring system was proposed. • Accuracy of the pseudo-labelling algorithm can be as high as 0.963. • Characteristics and variation of training data in classifier models were assessed. • Performance of classifier models can be improved through semi-supervised learning. • Techniques can be used for automated training data collection and model update. [ABSTRACT FROM AUTHOR]

To overcome challenges in multiple-object tracking (MOT) tasks, recent algorithms use interaction cues alongside motion and appearance features. These algorithms use graph neural networks or transformers to extract interaction features that lead to high computation costs. In this paper, a novel interaction cue based on geometric features is presented aiming to detect occlusion and reidentify lost targets with low computational costs. Moreover, in the majority of algorithms, camera motion is considered negligible, which is a strong assumption that is not always true and can lead to identity (ID) switching or mismatching of targets. In this paper, a method for measuring camera motion is presented that efficiently reduces its effect on tracking. The proposed algorithm is evaluated on MOT17 and MOT20 datasets and achieves state-of-the-art performance on MOT17 with comparable results on MOT20. The code is also publicly available. 1 1 https://github.com/mhnasseri/for_tracking. • Cascade association based on the detection score. • A new similarity metric that considers detection's size. • A novel interaction model for occlusion handling and target re-identification. • A novel algorithm for estimating camera motion and removing it. • State-of-the-art results on MOT17 and comparable results on MOT20. [ABSTRACT FROM AUTHOR]

• Rethinking the PASCAL-VOC and MS-COCO dataset for small object detection. • There are different labeling errors in these two benchmarks by visual analysis. • Building several specific datasets to analyze small object detection. • Data quality is another factor that affects the performance of small object detection. The data and the algorithm are critical to deep learning-based small object detectors. In this paper, we rethink the PASCAL-VOC and MS-COCO dataset for small object detection. By visual analysis of the original annotations, we find that there are different labeling errors in these two datasets. To solve these problems, we build specific datasets, including SDOD, Mini6K, Mini2022 and Mini6KClean. The experimental results of several typical algorithms (e.g. SSD, YOLOv5, Faster RCNN and Deformable DETR) on the datasets show that data labeling errors (such as missing labels, category label errors, inappropriate labels) are another factor that affects the detection performance of small objects. [ABSTRACT FROM AUTHOR]

In this paper, we propose forward and backward stochastic differential equations (FBSDEs) based deep neural network (DNN) learning algorithms for the solution of high dimensional quasi-linear parabolic partial differential equations (PDEs), which is related to the FBSDEs from the Pardoux-Peng theory. The algorithms rely on a learning process by minimizing the path-wise difference between two discrete stochastic processes, which are defined by the time discretization of the FBSDEs and the DNN representation of the PDE solution, respectively. The proposed algorithms are shown to generate DNN solution for a 100-dimensional Black–Scholes–Barenblatt equation, which is accurate in a finite region in the solution space, and has a convergence rate close to that of the Euler–Maruyama scheme used for discretizing the FBSDEs. • FBSDE deep neural network (DNN) with loss comparing two stochastic processes for the PDEs from Pardoux-Peng theory. • Strong 1/2 Convergence as the Euler-Maruyama method in solving a 100-dimensional Black-Scholes-Barenblatt equation. • Use of Richardson extrapolation for accuracy enhancement. • Multiscale DNN captures temporal high frequency content of the PDEs more accurately. [ABSTRACT FROM AUTHOR]

Person re-identification(ReID) is an intelligent video surveillance technology that retrieves the same person from different cameras. This task is extremely challenging due to changes in person poses, different camera views, and occlusion. In recent years, person ReID based on deep learning technology has received widespread attention due to the rapid development and excellent performance of deep learning. In this paper, we first divide person ReID based on deep learning approaches into seven types, i.e., fused hand-crafted features deep model, representation learning model, metric learning model, part-based deep model, video-based model, GAN-based model, unsupervised model. Furthermore, we launched a brief overview of the seven types. Then, we introduce some examples of commonly used datasets, compare the performance of some algorithms on image and video datasets in recent years, and analyze the advantages and disadvantages of various methods. Finally, we summarize the possible future research directions of person ReID technology. • Dividing person ReID based on deep learning approaches into seven types. • Introducing some examples of commonly used datasets. • Comparing the performance of some algorithms on image and video datasets in recent years. • Analyzing the advantages and disadvantages of various methods. • Summarizing the possible future research directions of person ReID technology. [ABSTRACT FROM AUTHOR]