3D model classification based on nonparametric discriminant analysis with kernels

IntroductionExisting multi-view-based 3D model classification methods have the problems of insufficient view refinement feature extraction and poor generalization ability of the network model, which makes it difficult to further improve the classification accuracy. To this end, this paper proposes a multi-view SoftPool attention convolutional network for 3D model classification tasks.MethodsThis method extracts multi-view features through ResNest and adaptive pooling modules, and the extracted features can better represent 3D models. Then, the results of the multi-view feature extraction processed using SoftPool are used as the Query for the self-attentive calculation, which enables the subsequent refinement extraction. We then input the attention scores calculated by Query and Key in the self-attention calculation into the mobile inverted bottleneck convolution, which effectively improves the generalization of the network model. Based on our proposed method, a compact 3D global descriptor is finally generated, achieving a high-accuracy 3D model classification performance.ResultsExperimental results showed that our method achieves 96.96% OA and 95.68% AA on ModelNet40 and 98.57% OA and 98.42% AA on ModelNet10.DiscussionCompared with a multitude of popular methods, our algorithm model achieves the state-of-the-art classification accuracy.

Deep learning based 3D model classification methods have poor effectiveness in fine-grained 3D model classification. Aiming at the problem, an end-to-end fine-grained 3D model classification framework is proposed, and a network based on deep ensemble learning network and context detail awareness module (CDAM) is constructed. Inputting the multiply views of a 3D model, the global shape features are extracted through the deep ensemble learning sub-network. And the local detail features are obtained through the auxiliary sub-network based on CDAM. Based on above two sub-networks, an end-to-end weakly supervision fine-grained 3D model classification network is constructed. Experiments are conducted on three sub-datasets with different levels of difficulties, Airplane, Chair and Car, from the public dataset FG3D. The classification accuracies for above three sub-datasets are 96.31%, 85.44% and 79.62% respectively, which demonstrate the fine classification performance and more generalization of the proposed method.

Dimensionality reduction is the most popular method for feature extraction and recognition. Recently, Li et al. (IEEE PAMI, 2009) proposed Nonparametric Discriminant Analysis (NDA) based dimensionality reduction for face recognition and reported an excellent recognition performance. However, NDA has its limitations on extracting the nonlinear features of face images for recognition, and owing to the highly nonlinear and complex distribution of face images under a perceivable variation in viewpoint, illumination or facial expression. In order to increase the NDA, we extend the NDA with kernel trick to propose Nonparametric Kernel Discriminant Analysis (NKDA) for feature extraction and recognition. Experimental results on ORL, YALE and UMIST face databases show that NKDA outperforms NDA on recognition, which demonstrates that it is feasible to improve NDA with kernel trick for feature extraction.

<p>Support vector machine (SVM) is a powerful classification methodology, where the support vectors fully describe the decision surface by incorporating local information. On the other hand, nonparametric discriminant analysis (NDA) is an improvement over LDA where the normality assumption is relaxed. NDA also detects the dominant normal directions to the decision plane. This paper introduces a novel SVM þNDA model which can be viewed as an extension to the SVM by incorporating some partially global information, especially, discriminatory information in the normal direction to the decision boundary. This can also be considered as an extension to the NDA where the support vectors improve the choice of k-nearest neighbors on the decision boundary by incorporating local information. Being an extension to both SVM and NDA, it can deal with heteroscedastic and non-normal data. It also avoids the small sample size problem. Moreover, it can be reduced to the classical SVM model, so that existing softwares can be used. A kernel extension of the model, called KSVM þ KNDA is also proposed to deal with nonlinear problems. We have carried an extensive comparison of the SVM þ NDA to the LDA, SVM, heteroscedastic LDA (HLDA), NDA and the combined SVM and LDA on artificial, real and face recognition data sets. Results for KSVM þ KNDA have also been presented. These comparisons demonstrate the advantages and superiority of our proposed model</p>

With the rapid advancement of 3D acquisition technologies, 3D sensors such as LiDARs, 3D scanners, and RGB-D cameras have become increasingly accessible and cost-effective. These sensors generate 3D point cloud data that require efficient algorithms for tasks such as 3D model classification and segmentation. While deep learning techniques have proven effective in these areas, existing models often rely on complex architectures, leading to high computational costs that are impractical for real-time applications like augmented reality and robotics. In this work, we propose the Multi-level Graph Convolutional Neural Network (MLGCN), an ultra-efficient model for 3D point cloud analysis. The MLGCN model utilizes shallow Graph Neural Network (GNN) blocks to extract features at various spatial locality levels, leveraging precomputed KNN graphs shared across GCN blocks. This approach significantly reduces computational overhead and memory usage, making the model well-suited for deployment on low-memory and low-CPU devices. Despite its efficiency, MLGCN achieves competitive performance in object classification and part segmentation tasks, demonstrating results comparable to state-of-the-art models while requiring up to a thousand times fewer floating-point operations and significantly less storage. The contributions of this paper include the introduction of a lightweight, multi-branch graph-based network for 3D shape analysis, the demonstration of the model's efficiency in both computation and storage, and a thorough theoretical and experimental evaluation of the model's performance. We also conduct ablation studies to assess the impact of different branches within the model, providing valuable insights into the role of specific components.

Existing class-incremental learning methods have achieved significant progress in unimodal domains, but they face severe challenges of catastrophic forgetting and cross-modal interference when handling multimodal data. We propose a causal intervention-based multimodal class-incremental learning framework to address the stability-plasticity trade-off in 3D model classification and retrieval tasks. By employing backdoor adjustment-based causal intervention, our approach decouples historical task biases from new knowledge acquisition. It introduces an alternating modality freezing strategy to isolate parameter updates between geometric (point cloud) and visual (multi-view) modalities, thereby suppressing cross-modal gradient interference. Furthermore, a dynamic feature anchoring loss is utilized to constrain feature space drift and maintain cross-task consistency. Experimental results on the ModelNet40 and ShapeNet-Core55 datasets demonstrate that our method achieves state-of-the-art performance compared to competitive baselines, confirming the effectiveness of multimodal redundancy in mitigating unimodal degradation. This work provides theoretical support and technical implementation pathways for lifelong learning systems in complex 3D scenarios.

In order to improve the classification effect of the 3D CAD model, this paper combines the knowledge recognition algorithm of convolutional neural network to construct the 3D CAD model classification model. Moreover, this paper analyzes the application of the convolutional neural network algorithm in the classification of 3D CAD models, improves the knowledge recognition algorithm, and builds the basic structure of the convolutional neural network. In addition, this paper builds an intelligent recognition model with the support of the improved algorithm, designs experiments to verify the effect of this paper, and draws a visual display statistical graph based on the statistical test results. Through experimental research, it can be known that the 3D CAD classification model based on the knowledge recognition algorithm of convolutional neural network proposed in this paper can effectively improve the classification effect of the CAD model.

This paper presents a novel approach for online subspace learning based on an incremental version of the nonparametric discriminant analysis (NDA). For many real-world applications (like the study of visual processes, for instance) it is impossible to know beforehand the number of total classes or the exact number of instances per class. This motivated us to propose a new algorithm, in which new samples can be added asynchronously, at different time stamps, as soon as they become available. The proposed technique for NDA-eigenspace representation has been used in pattern recognition applications, where classification of data has been performed based on the nearest neighbor rule. Extensive experiments have been carried out both in terms of classification accuracy and execution time. On the one hand, the results show that the Incremental NDA converges towards the classical NDA at the end of the learning process and furthermore. On the other hand, Incremental NDA is suitable to update a large knowledge representation eigenspace in real-time. Finally, the use of our method on a real-world application is presented.

Many state-of-the-art i-vector based voice biometric systems use linear discriminant analysis (LDA) as a post-processing stage to increase the computational efficiency in the back-end via dimensionality reduction, as well as annihilate the undesired (noisy) directions in the total variability subspace. The traditional approach for computing the LDA transform uses parametric representations for both intra- and inter-class scatter matrices that are based on the Gaussian distribution assumption. However, it is known that the actual distribution of i-vectors may not necessarily be Gaussian, and in particular, in the presence of noise and channel distortions. In addition, the rank of the LDA projection (i.e., the maximum number of available discriminant bases) is limited to the number of classes minus 1. Accordingly, language recognition tasks on noisy data that involve only a few language classes receive limited or no benefit from the LDA post-processing. Motivated by this observation, we present an alternative non-parametric discriminant analysis (NDA) technique that measures both the within- and between-language variation on a local basis using the nearest neighbor rule. The effectiveness of the NDA method is evaluated in the context of noisy language recognition tasks using speech material from the DARPA Robust Automatic Transcription of Speech (RATS) program. Experimental results indicate that NDA is more effective than the traditional parametric LDA for language recognition under noisy and channel degraded conditions.

With the development of 3D model reconstruction, manufacturing, and 3D model vision technologies, 3D model recognition has attracted much attention recently. To handle the 3D model recognition problem, in this paper, we propose a panorama based on multi-channel-attention (MCA) CNN network for the representation of the 3D model. The proposed method is composed of three parts: extracting views, transform function learning, and generating 3D model descriptor. Concretely, we first extract the 2D panoramic views for each 3D model, and we use the multi-channel-attention neural network to extract the descriptor for each 3D model. Here, the attention model is used to find the unequal weights of each panorama view to generate the more robust 3D model descriptor. Finally, The fusion feature is used to handle the 3D model classification and retrieval problem. The popular data sets ModelNet and ShapeNet are used to demonstrate the performance of our approach. The experiments also demonstrate the superiority of our proposed method over the state-of-art methods.

Recently, 3D model retrieval based on views has become a research hotspot. In this method, 3D models are represented as a collection of 2D projective views, which allows deep learning techniques to be used for 3D model classification and retrieval. However, current methods need improvements in both accuracy and efficiency. To solve these problems, we propose a new 3D model retrieval method, which includes index building and model retrieval. In the index building stage, 3D models in library are projected to generate a large number of views, and then representative views are selected and input into a well-learned convolutional neural network (CNN) to extract features. Next, the features are organized according to their labels to build indexes. In this stage, the views used for representing 3D models are reduced substantially on the premise of keeping enough information of 3D models. This method reduces the number of similarity matching by 87.8%. In retrieval, the 2D views of the input model are classified into a category with the CNN and voting algorithm, and then only the features of one category rather than all categories are chosen to perform similarity matching. In this way, the searching space for retrieval is reduced. In addition, the number of used views for retrieval is gradually increased. Once there is enough evidence to determine a 3D model, the retrieval process will be terminated ahead of time. The variable view matching method further reduces the number of similarity matching by 21.4%. Experiments on the rigid 3D model datasets ModelNet10 and ModelNet40 and the nonrigid 3D model dataset McGill10 show that the proposed method has achieved retrieval accuracy rates of 94%, 92%, and 100%, respectively.

Category-specific upright orientation estimation for 3D model classification and retrieval

Instance and prototype contrastive learning for multi-view 3D model retrieval and classification

Convolutional neural network (CNN) has shown superior classification results for hyperspectral image classification. Due to high dimensionality of the hyperspectral image, usually a feature reduction method is applied to the hyperspectral data before feeding it to the CNN model. Principal component analysis is the most widely used approach to this end. However, it has two main disadvantages. It uses the mean square error measure and ignores the class separability. Moreover, it is a pixel-based method, which does not utilize the spatial information. To deal with these weaknesses, the patch-based nonparametric discriminant analysis method is proposed for hyperspectral image feature reduction in this work. However, due to the complex and heterogeneous nature of the hyperspectral images, the use of fixed square patches is not so appropriate. To deal with this difficulty, a shaping approach is introduced for the generation of adaptive patches with consistent shapes in each local region. The input patches of the CNN model are also weighted according to the spectral similarity and class boundaries information. Moreover, a simple residual CNN model is suggested for the classification of the extracted shaped input patches. The efficiency of the proposed framework is assessed in different cases using various evaluation measures on six real hyperspectral images.

Biometrics serves to identify the identity of an individual with the help of mathematical analysis of its biological features. In this paper, we propose a novel classification method based on kernel Nonparametric Discriminant Analysis (KNDA). We use the facial features extracted with Gabor descriptor and ordinal filter, which are encoded in local regions, as visual primitives. The different ordinal measures are derived from various kinds of components of Gabor images such as magnitude, phase, real and imaginary. Then, the statistical distributions of these primitives in face image blocks are concatenated to obtain a feature vector whose dimension is reduced using PCA and variance. Each feature vector is treated as a feature input for the proposed Multi-class KNDA classifier. The proposed method incorporates some near-global variations of the data provided by the KNDA. In fact, this latter is based on flexible non-linear separation between face database classes. Moreover, it relaxes the normality assumption of the Linear Discriminant Analysis (LDA). The proposed method is tested on the well-known ORL face database and the Yale face database. Then, it is evaluatedand compared with non-linear classifier (KFD) and linear classifier (LDA) in term ofclassification accuracy.