Rethinking Video Anomaly Detection - A Continual Learning Approach

Most graph-network-based meta-learning approaches model instance-level relation of examples. We extend this idea further to explicitly model the distribution-level relation of one example to all other examples in a 1-vs-N manner. We propose a novel approach named distribution propagation graph network (DPGN) for few-shot learning. It conveys both the distribution-level relations and instance-level relations in each few-shot learning task. To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example. Equipped with dual graph architecture, DPGN propagates label information from labeled examples to unlabeled examples within several update generations. In extensive experiments on few-shot learning benchmarks, DPGN outperforms state-of-the-art results by a large margin in 5% $\sim$ 12% under supervised setting and 7% $\sim$ 13% under semi-supervised setting. Code will be released.

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. FSL tasks have been predominantly solved by leveraging the ideas from gradient-based meta-learning and metric learning approaches. However, recent works have demonstrated the significance of powerful feature representations with a simple embedding network that can outperform existing sophisticated FSL algorithms. In this work, we build on this insight and propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations. Equivariance or invariance has been employed standalone in the previous works; however, to the best of our knowledge, they have not been used jointly. Simultaneous optimization for both of these contrasting objectives allows the model to jointly learn features that are not only independent of the input transformation but also the features that encode the structure of geometric transformations. These complementary sets of features help generalize well to novel classes with only a few data samples. We achieve additional improvements by incorporating a novel self-supervised distillation objective. Our extensive experimentation shows that even without knowledge distillation our proposed method can outperform current state-of-the-art FSL methods on five popular benchmark datasets.

Driven by big data in wireless networks, the meta-learner-based scheme provides a promising paradigm to make full use of big data at the base stations to improve the per-formance of few-shot learning tasks, which plays an important role in facilitating network edge intelligence. However, it is a dilemma to balance the few-shot learning performance and the communication costs of meta-learner transmission. In this paper, we studied the fast adaptation of few-shot learning in wireless networks. First, a user grouping-based meta-learner generation scheme is designed, and a multicasting-based model transmission scheme is proposed. Second, a learning task selection scheme is designed to facilitate the fast adaptation to few-shot learning tasks at the users. Finally, the simulation results are provided to show that our proposed scheme can achieve model accuracy performance gains with low communication costs.

Recently, significant advancements have been made in few-shot learning (FSL) methods based on metric learning, which have been widely applied to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). These methods typically require experimental samples to exhibit sufficiently small intra-class distances. However, in practical applications, SAR target samples are often acquired under varying depression angles, resulting in mixed images. The inherent feature deviations caused by variations in depression angles lead to increased intra-class distances in the feature distribution, which adversely affects recognition performance. To address this challenge, we propose a novel approach called the Dense Graph Prototype Network (DGP-Net). DGP-Net addresses the feature deviation problem by learning potential features and utilizes feature distribution modeling for classification. Specifically, by leveraging the information propagation mechanism of a densely connected Graph Convolutional Network (GCN), potential features are iteratively learned while retaining previous features, thereby clustering samples of the same class with different elevation angles and eliminating feature deviations. To avoid sampling examples located at the edges of the distribution in FSL tasks, which may lead to inaccurate GCN information propagation, we introduce a ”prototype node” mechanism to enhance the robustness of the model. We conduct experiments using samples from the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark dataset with varying elevation angles for the same class. Experimental results on this dataset demonstrate the superior performance of DGP-Net. Specifically, in 3-way and 5-way classification tasks, the recognition accuracy of DGP-Net improved by over 4% compared to state-of-the-art (SOTA) methods. The source code for DGP-Net is available at https://github.com/Zhou-xy99/DGP-Net.

The continual learning and development are significant for robots to learn multiple tasks sequentially. The difficulty lies in balancing the efficient learning of new tasks and overcoming catastrophic forgetting of old tasks. Although many continual learning methods have been proposed for pattern recognition, continual reinforcement learning methods for redundant musculoskeletal and robotic systems are few and have limitations. Therefore, inspired by the developmental mechanisms in motor cortex, this article proposes a neural manifold modulated continual reinforcement learning method for musculoskeletal and robotic systems. First, a recurrent neural network (RNN) with an expected neural manifold is designed and conditions of weights are derived. Second, the ability of projectors for characterizing the neural manifold within RNN is analyzed. Furthermore, a continual reinforcement learning method of RNN is proposed with the modulation of a neural manifold. The method is validated by redundant musculoskeletal and robotic systems in simulation. The results suggest that it can realize continual reinforcement learning of multiple tasks in different movements and environments. Furthermore, compared with related works, the proposed method achieves better performance.

BackgroundThe location of retinal vessels is an important prerequisite for Central Serous Chorioretinopathy (CSC) Laser Surgery, which does not only assist the ophthalmologist in marking the location of the leakage point (LP) on the fundus color image but also avoids the damage of the laser spot to the vessel tissue, as well as the low efficiency of the surgery caused by the absorption of laser energy by retinal vessels. In acquiring an excellent intra- and cross-domain adaptability, the existing deep learning (DL)-based vessel segmentation scheme must be driven by big data, which makes the densely annotated work tedious and costly.MethodsThis paper aims to explore a new vessel segmentation method with a few samples and annotations to alleviate the above problems. Firstly, a key solution is presented to transform the vessel segmentation scene into the few-shot learning task, which lays a foundation for the vessel segmentation task with a few samples and annotations. Then, we improve the existing few-shot learning framework as our baseline model to adapt to the vessel segmentation scenario. Next, the baseline model is upgraded from the following three aspects: (1) A multi-scale class prototype extraction technique is designed to obtain more sufficient vessel features for better utilizing the information from the support images; (2) The multi-scale vessel features of the query images, inferred by the support image class prototype information, are gradually fused to provide more effective guidance for the vessel extraction tasks; and (3) A multi-scale attention module is proposed to promote the consideration of the global information in the upgraded model to assist vessel localization. Concurrently, the integrated framework is further conceived to appropriately alleviate the low performance of a single model in the cross-domain vessel segmentation scene, enabling to boost the domain adaptabilities of both the baseline and the upgraded models.ResultsExtensive experiments showed that the upgraded operation could further improve the performance of vessel segmentation significantly. Compared with the listed methods, both the baseline and the upgraded models achieved competitive results on the three public retinal image datasets (i.e., CHASE_DB, DRIVE, and STARE). In the practical application of private CSC datasets, the integrated scheme partially enhanced the domain adaptabilities of the two proposed models.

In the marine ecological environment, marine microalgae is an important photosynthetic autotrophic organism, which can carry out photosynthesis and absorb carbon dioxide. With the increasingly serious eutrophication of the water body, under certain environmental factors, the rapid propagation of some algae in the water body gradually forms a harmful bloom, which damages the water environment. Therefore, how to identify the beneficial algae and harmful algae quickly and accurately has gradually become the key to solve the problem. There are more than 30,000 species of marine microalgae in the world, and the sample data are few and the characteristics are not obvious. Many of the algae are similar in shape and difficult to distinguish. The few-shot learning task is very challenging. By training very few labeled samples, the deep learning model has excellent recognition ability. Meanwhile, the few-shot classification method based on metric learning has attracted considerable attention. In this paper, in order to make full use of image features and improve the generalization ability of the model, a multi-scale local feature fusion algorithm was proposed to classify marine microalgae with few shots. First, the input image is gridded and multiscale processed, and then it is sent to the CTM category traversal module for feature extraction to obtain local features. A local feature fusion module based on the SE-NET self-attention mechanism is designed to obtain local enhanced features containing global information to improve the generalization ability of the model. Classification is realized by calculating the distance between the sample feature vector of the query set and the prototype of the support set. Under the settings of 5-way 1-shot and 5-way 5-shot, the classification accuracy of the proposed method is improved by 6.08% and 5.5%, respectively. It provides a new idea for microalgae identification and a new opportunity for the sustainable development of new energy.

As one of the most common sports injuries, lateral ankle sprains often lead to chronic lateral ankle instability (CLAI), which may require ankle lateral stabilization surgery to enhance ankle stability. Postoperative rehabilitation is crucial for patients to regain pre-injury sports capabilities, yet traditional rehabilitation methods are time-consuming and costly, relying heavily on subjective and objective clinical assessments. Therefore, this study has developed a wearable intelligent telerehabilitation device designed to offer cost-effective postoperative rehabilitation progress evaluations for CLAI patients. The developed device integrates a portable sensor system including pressure insoles and inertial measurement units (IMUs) to capture gait and biomechanical data, and an evaluation algorithm employing few-shot learning model to enhance model performance with small datasets. The system was trained and tested using gait data collected from 102 patients, labelled by a professional clinician with over 20 years of surgical experiences through subjective self-reported fuctions, physical evaluation, and objective examination. In the test stage, the system demonstrated an accuracy of 0.89, recall of 0.88, specificity of 0.89, and an overall F1 score of 0.90, initially fulfills the clinical requirements. Compared to traditional machine learning models, the few-shot learning approach improved accuracy by at least 0.17 and the F1-score by 0.13. The device's cost-effectiveness, ease of use, and high repeatability make it a promising tool for at-scale both clinical and home-based rehabilitation. Besides, this study creatively introduced the few-shot learning method to the field of rehabilitation, offering a solution to address the challenge of limited high-quality data in rehabilitation studies, promoting the development of intelligent healthcare.

Deep learning has been rapidly developed and obtained great achievements with a dataintensive condition. However, sufficient datasets are not always available in practical application. In the absence of data, humans can still perform well in studying and recognizing new items while it becomes a hard task for the computer to learn and generate from a small dataset. Thus, researchers are increasingly interested in few-shot learning. The purpose of few-shot learning is to allow computers to carry out unknown tasks with a few examples. Recently, effective few-shot models have frequently been designed using transfer learning approaches, with the metric method being an important branch in transfer learning. This article reviews the metric methodologies for few-short learning, analyzing the development of the metric based few-shot learning in the following three categories: traditional metric methods, relation network based metric methods and graph based metric methods. Then it compares the effectiveness of those models on a representative dataset and illustrates the feature of each category. Finally, it discusses the potential future research fields.

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.

Continual learning systems suffer from catastrophic forgetting, where updates for new tasks destructively interfere with previously acquired knowledge. Recent empirical advances—including flatness-based optimization, static–dynamic architectural decomposition, and probabilistic reg- ularization— have demonstrated strong mitigation of forgetting. However, a unified structural explanation for why these methods succeed remains underdeveloped. This paper proposes a constraint geometry perspective on representation updates in continual learning. We argue that catastrophic forgetting can be interpreted as a curvature-induced vio- lation of constraint-preserving update dynamics. Under this view, successful continual learning methods implicitly regulate update directions in high-curvature regions of the loss landscape. Rather than introducing a new algorithm, this work provides a structural interpretation that clarifies why diverse empirical strategies succeed. Identifying and preserving geometric constraints during gradient-based updates may serve as a guiding principle for future continual learning research.

Many deep learning architectures have been employed to model the semantic compositionality for text sequences, requiring a huge amount of supervised data for parameters training, making it unfeasible in situations where numerous annotated samples are not available or even do not exist. Different from data-hungry deep models, lightweight word embedding-based models could represent text sequences in a plug-and-play way due to their parameter-free property. In this paper, a modified hierarchical pooling strategy over pre-trained word embeddings is proposed for text classification in a few-shot transfer learning way. The model leverages and transfers knowledge obtained from some source domains to recognize and classify the unseen text sequences with just a handful of support examples in the target problem domain. The extensive experiments on five datasets including both English and Chinese text demonstrate that the simple word embedding-based models (SWEMs) with parameter-free pooling operations are able to abstract and represent the semantic text. The proposed modified hierarchical pooling method exhibits significant classification performance in the few-shot transfer learning tasks compared with other alternative methods.

Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on ‘blurry’ task boundary; where tasks shares classes and is more realistic and practical. To address such task, we argue the importance of diversity of samples in an episodic memory. To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM). With extensive empirical validations on MNIST, CIFAR10, CIFAR100, and ImageNet datasets, we show that the proposed method significantly improves the accuracy in blurry continual learning setups, outperforming state of the arts by large margins despite its simplicity. Code and data splits will be available in https://github.com/clovaai/rainbow-memory.

Few-shot learning aims to learn generalized knowledge from limited data, which is a challenging study. Metric-based few-shot learning is the most widely studied direction, and most metric-based methods focus on how to learn a more robust feature embedding space or distance metric for classification. Few-shot learning is trained with a large number of tasks. Most existing methods do not realize that the role of the same sample in different learning tasks may be different, which will affect the effectiveness of classification. This paper proposes a task-adaptive feature adjustment method to obtain new features with task context information and more discrimination to solve this problem. We also introduce the Sphere manifold into few-shot learning, use the manifold metric instead of the Euclidean metric, and deduce the gradient optimization on the manifold. We propose a novel few-shot learning method with an excellent performance by combining these two innovations. We conduct several experiments on the few-shot learning benchmark datasets to demonstrate the advancement of our methods. The experimental results have significantly improved over the baseline and are highly competitive with the mainstream and effective methods.

Emergency medicine represents the front line of healthcare delivery, where swift decision-making, clinical precision, and effective use of diagnostic tools can mean the difference between life and death. Among the many diagnostic technologies available in the emergency department (ED), the electrocardiogram (ECG) remains one of the most essential and frequently used tools. It provides rapid, non-invasive insight into cardiac function, guiding immediate management for patients presenting with chest pain, palpitations, syncope, dyspnea, or altered mental status. This work, “Advanced Clinical Insights in Emergency Medicine & ECG,” aims to bridge the gap between foundational ECG interpretation and the nuanced decision-making required in acute clinical settings. It explores not only the technical aspects of ECG acquisition and analysis but also the practical challenges such as artifact recognition, misinterpretation risks, and the integration of ECG findings with broader clinical assessments. Emphasis is placed on real-world scenarios where the ECG must be interpreted under pressure, often with limited information and high stakes. Through focused discussion on advanced ECG patterns, common pitfalls, and clinical case insights, this compilation serves as a resource for emergency physicians, residents, medical students, nurses, and paramedics. By highlighting both the power and the limitations of ECG in emergency care, it encourages critical thinking, continuous learning, and collaborative practice. In an era of evolving technologies and expanding clinical responsibilities, the need for accurate, rapid, and context-aware ECG interpretation has never been greater. It is our hope that this text enhances diagnostic confidence, reduces error rates, and ultimately contributes to improved patient outcomes in emergency medicine.