Classical Embedding Research Articles

Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks. Though greatly promoted the development of these fields, existing works mainly focus on learning the region embeddings of different attribute features and neglect the importance of discriminative attribute localization. It is also unclear whether the learned attention truly matches the real human attention. To tackle this problem, this paper proposes to employ real human gaze data for visual recognition networks to learn from human attention. Specifically, we design a unified Attribute Attention Network (A 2Net) that learns from human attention for both ZSL and FGVC tasks. The overall model consists of an attribute attention branch and a baseline classification network. On top of the image feature maps provided by the baseline classification network, the attribute attention branch employs attribute prototypes to produce attribute attention maps and attribute features. The attribute attention maps are converted to gaze-like attentions to be aligned with real human gaze attention. To guarantee the effectiveness of attribute feature learning, we further align the extracted attribute features with attribute-defined class embeddings. To facilitate learning from human gaze attention for the visual recognition problems, we design a bird classification game to collect real human gaze data using the CUB dataset via an eye-tracker device. Experiments on ZSL and FGVC tasks without/with real human gaze data validate the benefits and accuracy of our proposed model. This work supports the promising benefits of collecting human gaze datasets and automatic gaze estimation algorithms learning from human attention for high-level computer vision tasks.

On hyperelliptic curves of odd degree and genus g with 6 torsion points of order 2g + 1

Let a hyperelliptic curve C of genus g defined over an algebraically closed field K of characteristic 0, given by the equation y2=f(x), where the polynomial f(x)∈K[x]is square-free and has odd degree 2g+1. The curve Ccontains a single “infinite” point O, which is the Weierstrass point. There is a classical embedding of C(K)into the group of K-points J(K)of the Jacobian variety Jof the curve C, identifying the point Owith the unit element of the group J(K). For 2≤g≤5, the article explicitly found representatives of birational equivalence classes such hyperelliptic curves Cwith a marked unique point at infinity Othat the set C(K)∩J(K)contains at least 6 torsion points of order 2g+1. It was previously known that for g=2there are exactly 5 such equivalence classes, and for g≥3an upper bound was known that depended only on the genus of g. We improve the previously known upper bound by almost 36 times.

Embedded Many‐Body Green's Function Methods for Electronic Excitations in Complex Molecular Systems

ABSTRACTMany‐body Green's function theory in the GW approximation with the Bethe–Salpeter equation (BSE) provides a powerful framework for the first‐principles calculations of single‐particle and electron–hole excitations in perfect crystals and molecules alike. Application to complex molecular systems, for example, solvated dyes, molecular aggregates, thin films, interfaces, or macromolecules, is particularly challenging as they contain a prohibitively large number of atoms. Exploiting the often localized nature of excitation in such disordered systems, several methods have recently been developed in which GW‐BSE is applied to a smaller, tractable region of interest that is embedded into an environment described with a lower‐level method. Here, we review the various strategies proposed for such embedded many‐body Green's functions approaches, including quantum–quantum and quantum–classical embeddings, and focus in particular on how they include environment screening effects either intrinsically in the screened Coulomb interaction in the GW and BSE steps or via extrinsic electrostatic couplings.

Adaptive class token knowledge distillation for efficient vision transformer

The Vision Transformer (ViT) outperforms Convolutional Neural Networks (CNNs) but at the cost of significantly higher computational demands. Knowledge Distillation (KD) has shown promise in compressing complex networks by transferring knowledge from a large pre-trained model to a smaller one. However, current KD methods for ViT often rely on CNNs as teachers or neglect the importance of class token ([CLS]) information, resulting in ineffective distillation of ViT’s unique knowledge. In this paper, we propose Adaptive Class token Knowledge Distillation ([CLS]-KD), which fully exploits information from the class token and patches in ViT. For class embedding (CLS) distillation, the intermediate CLS of the student model is aligned with the corresponding CLS of the teacher model through a projector. Furthermore, we introduce CLS-patch attention map distillation, where an attention map between the CLS and patch embeddings is generated and matched at each layer. This empowers the student model to learn how to dynamically extract patch embedding information into the CLS under teacher guidance. Finally, we propose Adaptive Layer-wise Distillation (ALD) to mitigate the imbalance in distillation effects varying with the depth of layers. This method assigns greater weight to the losses in layers where the training discrepancies between the teacher and student models are larger during distillation. Through these strategies, [CLS]-KD consistently surpasses existing state-of-the-art methods on the ImageNet-1K dataset across various teacher-student configurations. Furthermore, the proposed method demonstrates its generalization capability through transfer learning experiments on the CIFAR-10, CIFAR-100, and CALTECH-256 datasets.

Relative injective modules, superstability and noetherian categories

We study classes of modules closed under direct sums, [Formula: see text]-submodules and [Formula: see text]-epimorphic images where [Formula: see text] is either the class of embeddings, RD-embeddings or pure embeddings. We show that the [Formula: see text]-injective modules of theses classes satisfy a Baer-like criterion. In particular, injective modules, RD-injective modules, pure injective modules, flat cotorsion modules and [Formula: see text]-torsion pure injective modules satisfy this criterion. The argument presented is a model theoretic one. We use in an essential way stable independence relations which generalize Shelah’s non-forking to abstract elementary classes. We show that the classical model theoretic notion of superstability is equivalent to the algebraic notion of a noetherian category for these classes. We use this equivalence to characterize noetherian rings, pure semisimple rings, perfect rings and finite products of finite rings and artinian valuation rings via superstability.

On the modulus of continuity of fractional Orlicz-Sobolev functions

AbstractNecessary and sufficient conditions are presented for a fractional Orlicz-Sobolev space on $${\mathbb {R}}^n$$ R n to be continuously embedded into a space of uniformly continuous functions. The optimal modulus of continuity is exhibited whenever these conditions are fulfilled. These results pertain to the supercritical Sobolev regime and complement earlier sharp embeddings into rearrangement-invariant spaces concerning the subcritical setting. Classical embeddings for fractional Sobolev spaces into Hölder spaces are recovered as special instances. Proofs require novel strategies, since customary methods fail to produce optimal conclusions.

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions*

Abstract Induction motors play a vital role in the cooling water supply system of hydropower facilities. However, it is not feasible to collect sufficient fault samples in a hydropower station. The scarcity of labeled samples poses a challenge in developing powerful diagnostic models with high classification accuracy. To address this challenge, this paper proposes a multi-channel data fusion strategy based on a transformer for feature enhancement. Initially, the original signals are transferred into non-overlapping single-channel data patches to preserve correlation features across different channels. Next, temporal and spatial attention modules are applied to process the data patches, which can learn and fuse temporal and spatial information, respectively. Subsequently, the data patches are embedded to retain position information and represent fault-related features through class embedding, which are further processed by a transformer encoder with self-attention mechanisms. Finally, the classification task is achieved by using a multilayer perceptron layer connected to the class embedding. While dealing with limited training samples, the proposed method can learn robust features that are beneficial to improve the fault diagnosis ability of induction motors. The comparison of the proposed method with three basic models and two improved methods demonstrates the superiority of the proposed method in accuracy and feature clustering performance under limited sample conditions. In addition, ablation experiments demonstrate the necessity of each module in the proposed method.

Prompt-guided DETR with RoI-pruned masked attention for open-vocabulary object detection

Prompt-OVD is an efficient and effective DETR-based framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in base and novel classes. Additionally, our RoI-pruned masked attention helps leverage the zero-shot classification ability of the Vision Transformer-based CLIP, resulting in improved detection performance at a minimal computational cost. Our experiments on the OV-COCO and OV-LVIS datasets demonstrate that Prompt-OVD achieves an impressive 21.2 times faster inference speed than the first end-to-end open-vocabulary detection method (OV-DETR), while also achieving higher APs than four two-stage methods operating within similar inference time ranges. We release the code at https://github.com/DISL-Lab/Prompt-OVD.

Contrastive and uncertainty-aware nuclei segmentation and classification

Nuclei segmentation and classification play a crucial role in pathology diagnosis, enabling pathologists to analyze cellular characteristics accurately. Overlapping cluster nuclei, misdetection of small-scale nuclei, and pleomorphic nuclei-induced misclassification have always been major challenges in the nuclei segmentation and classification tasks. To this end, we introduce an auxiliary task of nuclei boundary-guided contrastive learning to enhance the representativeness and discriminative power of visual features, particularly for addressing the challenge posed by the unclear contours of adherent nuclei and small nuclei. In addition, misclassifications resulting from pleomorphic nuclei often exhibit low classification confidence, indicating a high level of uncertainty. To mitigate misclassification, we capitalize on the characteristic clustering of similar cells to propose a locality-aware class embedding module, offering a regional perspective to capture category information. Moreover, we address uncertain classification in densely aggregated nuclei by designing a top-k uncertainty attention module that leverages deep features to enhance shallow features, thereby improving the learning of contextual semantic information. We demonstrate that the proposed network outperforms the off-the-shelf methods in both nuclei segmentation and classification experiments, achieving the state-of-the-art performance.

Fate of charged wormhole structures utilizing Karmarkar approach

The purpose of this study is to elaborate on the Morris–Thorne wormhole notion by creating a detailed model of a charged wormhole shape function. The classical embedding theory, which has played a significant role in the general theory of relativity, accomplishes this objective. Here, we assume redshift function along with charge i.e. ψ(r,Q2)=Log[1+Q2r2] and Q(r)=ξr. For this particular choice, the surface redshift function remains positive and finite everywhere even for the larger range of radial coordinate r. In wormhole geometry, the violation of Null energy condition have a crucial role which leads to the exotic matter. We examined our solutions through energy bounds (Null, Weak and Strong energy bounds) to check their stable state and its viability. Interestingly, in present work we analyze that the presence of electric charge amplify the results and provides the traversable charged wormhole solutions without exotic matter near the throat in the context of general theory of relativity.

A global higher regularity result for the static relaxed micromorphic model on smooth domains

We derive a global higher regularity result for weak solutions of the linear relaxed micromorphic model on smooth domains. The governing equations consist of a linear elliptic system of partial differential equations that is coupled with a system of Maxwell-type. The result is obtained by combining a Helmholtz decomposition argument with regularity results for linear elliptic systems and the classical embedding of $H(\operatorname {div};\Omega )\cap H_0(\operatorname {curl};\Omega )$ into $H^1(\Omega )$ .

Federated Learning With Only Positive Labels by Exploring Label Correlations.

Federated learning (FL) aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this article, we study the multilabel classification (MLC) problem under the FL setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data with respect to a single class label is provided for each client. This issue can be addressed by adding a specially designed regularizer on the server side. Although effective sometimes, the label correlations are simply ignored and thus suboptimal performance may be obtained. Besides, it is expensive and unsafe to exchange user's private embeddings between server and clients frequently, especially when training model in the contrastive way. To remedy these drawbacks, we propose a novel and generic method termed federated averaging (FedAvg) by exploring label correlations (FedALCs). Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training. To further improve the safety and also reduce the communication overhead, we propose a variant to learn fixed class embedding for each client, so that the server and clients only need to exchange class embeddings once. Extensive experiments on multiple popular datasets demonstrate that our FedALC can significantly outperform the existing counterparts.

Particle Swarm Optimization for 5g and Beyond

Network embedding assigns nodes in a network to low dimensional representations and effectively preserves the network structure. Recently, a significant amount of progresses has been made toward this emerging network analysis paradigm. In this survey, we focus on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions. We first summarize the motivation of network embedding. Particle Swarm Optimization (PSO) algorithm is used as the proposed method. We discuss the classical graph embedding algorithms on cognitive radio environment and their relationship with network embedding. Afterwards and primarily, we provide a comprehensive overview of a large number of networks embedding methods in a systematic manner, covering the structure- and property-preserving network embedding methods, the network embedding methods with side information and the advanced information preserving network embedding methods. Moreover, several evaluation approaches for network embedding and some useful online resources, including the network data sets and software, are reviewed, too. Finally, we discuss the framework of exploiting these network embedding methods to build an effective system and point out some potential future directions. Key Word: Particle Swarm Optimization (PSO), Beyond 5G (B5G), Internet of Think (IOT), Machine Learning (ML)etc..

Fair large kernel embedding with relation-specific features extraction for link prediction

Knowledge graph embedding is a crucial technique for addressing the challenge of incomplete knowledge graphs, and convolutional neural networks are widely applied in this domain. However, convolutional neural networks face limitations in effectively capturing long-range dependencies between entities and relations in feature maps. Moreover, existing knowledge graph embedding models often adopt a uniform perspective on all relations within a knowledge graph, thereby overlooking the relation-specific features. To address the two issues, two novel knowledge graph embedding models, Large Kernel Embedding (LKE) and Large Kernel Embedding with Relation-specific Features Extraction (LKER), are proposed. The effectiveness of knowledge graph embedding is improved by integrating fair large kernel attention and introducing a parallel branch for relation-specific feature extraction in these models. Specifically, fair large kernel attention is incorporated into LKE, capturing long-range dependencies within the model. Based on LKE, LKER adds a parallel relationship-specific feature extraction branch to obtain more comprehensive relationship-specific feature information. The proposed models are extensively evaluated on five benchmark datasets, and the results show that the proposed models yield significant performance improvements in link prediction compared to classical and latest knowledge graph embedding models.

TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients

Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years. In federated learning, a central server periodically coordinates models with clients and aggregates the models trained locally by clients without necessitating access to local data. Despite its potential, the implementation of federated learning continues to encounter several challenges, predominantly the slow convergence that is largely due to data heterogeneity. The slow convergence becomes particularly problematic in cross-device federated learning scenarios where clients may be strongly limited by computing power and storage space, and hence counteracting methods that induce additional computation or memory cost on the client side such as auxiliary objective terms and larger training iterations can be impractical. In this paper, we propose a novel federated aggregation strategy, TurboSVM-FL, that poses no additional computation burden on the client side and can significantly accelerate convergence for federated classification task, especially when clients are "lazy" and train their models solely for few epochs for next global aggregation. TurboSVM-FL extensively utilizes support vector machine to conduct selective aggregation and max-margin spread-out regularization on class embeddings. We evaluate TurboSVM-FL on multiple datasets including FEMNIST, CelebA, and Shakespeare using user-independent validation with non-iid data distribution. Our results show that TurboSVM-FL can significantly outperform existing popular algorithms on convergence rate and reduce communication rounds while delivering better test metrics including accuracy, F1 score, and MCC.

Unsupervised twitter social bot detection using deep contrastive graph clustering

The emergence of malicious Twitter social bots poses a considerable threat to the security of social networks, and the detection of evolving social bots has become challenging. State-of-the-art detection methods are usually supervised, but the label acquisition process suffers from time-consuming and inaccurate problems in addition to its inability to cope with the challenge of the continuous evolution of social bots. Moreover, structural relationships within social networks are under-explored using current unsupervised methods. To address current challenges, we propose an unsupervised social bot detection method based on deep contrastive graph clustering (BotDCGC). This approach utilises a graph attentional encoder and an inner product decoder to acquire user node embeddings. By incorporating information from both user account features and topological structure, the model employs a contrastive learning technique based on structure to discern node embeddings of distinct classes within the feature space. Subsequently, confident cluster assignments are used as soft labels to guide the embedding process by calculating the similarity between each node and the clustering centre, enabling the joint optimisation of user node embeddings and clustering results. Experiments show that BotDCGC is more effective than the state-of-the-art baselines with an accuracy of 0.8095 in the Twibot-20 dataset and 0.9334 in the Cresci-2015 dataset, and the experimental results indicate the effectiveness of the graph autoencoder module, contrastive learning and deep clustering module.

Zero-Shot Aerial Object Detection with Visual Description Regularization

Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to address the challenge with prior descriptions of their visual appearance. Instead of directly encoding the descriptions into class embedding space which suffers from the representation gap problem, we propose to infuse the prior inter-class visual similarity conveyed in the descriptions into the embedding learning. The infusion process is accomplished with a newly designed similarity-aware triplet loss which incorporates structured regularization on the representation space. We conduct extensive experiments with three challenging aerial object detection datasets, including DIOR, xView, and DOTA. The results demonstrate that DescReg significantly outperforms the state-of-the-art ZSD methods with complex projection designs and generative frameworks, e.g., DescReg outperforms best reported ZSD method on DIOR by 4.5 mAP on unseen classes and 8.1 in HM. We further show the generalizability of DescReg by integrating it into generative ZSD methods as well as varying the detection architecture. Codes will be released at https://github.com/zq-zang/DescReg.

CAM based fine-grained spatial feature supervision for hierarchical yoga pose classification using multi-stage transfer learning

In this paper, we propose a technique for hierarchical yoga pose classification (YPC) in a multi-stage multi-tasking framework. We propose a three-stage transfer learning based end-to-end training methodology. Novelty lies in (a) proposed supervised contrastive combined loss function for stage-1 training, (b) proposed Encoder–Decoder network architecture with attention mechanism for stage-3 training, (c) proposed spatial context aware multi-tasking combined loss function for stage-3 training. Firstly, for stage-1 training, we propose the usage of linear combination of three loss functions: cross-entropy, self-supervised contrastive loss and supervised contrastive loss in a multi-tasking manner. We introduce radial and cosine margin into the formulation of self-supervised and supervised contrastive loss to pull feature embeddings of same class closer together compared to feature embeddings of different classes. Weights learned over stage-1 training are subsequently fine-tuned over cross-entropy multi-tasking loss in stage-2. These stage-2 weights are transfer learned and are further fine-tuned in stage-3 training. For stage-3 training, we propose the usage of spatial context aware multi-tasking combined loss function. This loss function leverages on the fine-grained spatial features obtained from HiResCAM. These are processed in parallel with features obtained from XGrad-CAM (sensitivity and conservation axioms satisfying features) to further supervise the learning of hierarchical yoga pose classifier. We exemplify our methodology on the publicly available Yoga-82 large-scale dataset. We report peak Top-1 YPC accuracy of 95.89% over 6 pose classes (Yoga-6), 93.85% over 20 pose classes (Yoga-20) and 90.0% over 82 pose classes (Yoga-82). Our proposed method achieves 6.1% improvement over Top-1 classification accuracy in Yoga-6 hierarchy, 9.3% improvement in Yoga-20 hierarchy and 10.9% improvement in Yoga-82 hierarchy in comparison with state-of-the-art (SOTA) methodology. We achieve the current best Top-1 classification accuracies in all the three YPC hierarchies.

An h$h$‐principle for embeddings transverse to a contact structure

AbstractGiven a class of embeddings into a contact or a symplectic manifold, we give a sufficient condition, that we call isocontact or isosymplectic realization, for this class to satisfy a general ‐principle. The flexibility follows from the ‐principles for isocontact and isosymplectic embeddings, it provides a framework for classical results, and we give two new applications. Our main result is that embeddings transverse to a contact structure satisfy a full ‐principle in two cases: if the complement of the embedding is overtwisted, or when the intersection of the image of the formal derivative with the contact structure is strictly contained in a proper symplectic subbundle. We illustrate the general framework on symplectic manifolds by studying the universality of Hamiltonian dynamics on regular level sets via a class of embeddings.

CR-TransR: A Knowledge Graph Embedding Model for Cultural Domain

As a combination of information computing technology and the cultural field, cultural computing is gaining more attention. The knowledge graph is also gradually applied as a particular data structure in the cultural area. Based on the domain knowledge graph data of the Beijing Municipal Social Science Project “Mining and Utilization of Cultural Resources in the Ancient Capital of Beijing,” this article proposes a graph representation learning model CR-TransR that integrates cultural attributes. Through the analysis of the data in the cultural field of the ancient capital of Beijing, a cultural feature dictionary is constructed, and a domain-specific feature matrix is constructed in the form of word vector splicing. The feature matrix is used to constrain the embedding graph model TransR, and then the feature matrix and the TransR model are jointly trained to complete the embedded expression of the knowledge graph. Finally, a comparative experiment is carried out on the Beijing ancient capital cultural knowledge graph dataset and the effects of the classic graph embedding algorithms TransE, TransH, and TransR. At the same time, we try to reproduce the embedding method with the core idea of neighbor node information aggregation as the core idea, and CRTransR are compared. The experimental tasks include link prediction and triplet classification, and the experimental results show that the CRTransR model performs better.