Single-label and multi-label conceptor classifiers in pre-trained neural networks

Qian, Guangwu; Zhang, Lei; Wang, Yan

doi:10.1007/s00521-018-3432-2

Cited by 6 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BPNN models employed for layer categorization in semi-infinite seabed, single sediment layer, and double sediment layer environments are denoted as NET-2-X, where X represents the specific environment (X=1, 2, 3). In total, four BPNN models are trained (Qian et al, 2019).…”

Section: Bpnn Inversion Model Of Geoacoustic Parameters Inversionmentioning

confidence: 99%

A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

Wang,

Cui,

Zhu

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

IntroductionExisting methods primarily focus on earth acoustic parameters inversion under specific layered structures. However, they face challenges with experimental data from unknown seabed stratification, hindering accurate parameter inversion.MethodsTo address this, a novel algorithm combines Back Propagation Neural Network (BPNN) for distinguishing seabed stratification and inverting acoustic parameters. Simulated sound pressure data disturb seabed parameters as input, enabling feature recognition for training the neural network inversion model. Acoustic parameters are then estimated under identified stratification using the sound field model.ResultsThe inversion model is validated using simulation and pool shrinkage data. Results show the neural network model effectively stratifies simulation and experimental data, providing accurate inversion results for acoustic parameters corresponding to distinct layers.DiscussionThe neural network model's accuracy and practicality are confirmed through hierarchical judgment of scale test data and acoustic parameter inversion. This approach introduces a new perspective for shallow sea acoustic parameter inversion, offering a promising application scenario.

show abstract

Section: Bpnn Inversion Model Of Geoacoustic Parameters Inversionmentioning

confidence: 99%

A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

Wang,

Cui,

Zhu

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…where  denotes the motion feature calculation parameter, and construct the shared feature subspace [16] according to  . To improve the use effect of the classifier designed in this paper, the support vector machine is integrated with some theories of multi-labeling transfer learning, and a multi-labeling classifier is constructed, which regards the labels of motion posture features [17] as…”

Section: Feature Extraction Of Hmpmentioning

confidence: 99%

Estimation of Human Motion Posture Using Multi-labeling Transfer Learning

Wang

Ren

et al. 2023

Braz. arch. biol. technol.

View full text Add to dashboard Cite

Human posture estimation is the basis of many computer vision tasks, such as motion recognition, violence detection and behavior understanding. Therefore, it is of great significance to study the estimation algorithm of human motion posture (HMP). To address the problem of poor estimation effect of traditional HMP estimation algorithm, in this paper, an estimation algorithm for HMP using multi-labeling transfer learning is proposed. First, the original human motion image is labeled by using the multi-label transfer learning, the HMP features are extracted, and the original image classification is completed. Second, a regulator is constructed based on the classification results of the original image, and the regulator is used to adjust the estimation results of HMP based on a convolutional neural networks. Finally, the posture compensation function is used to compensate for the error part to realize the estimation of HMP. In the experiment, the Human3.6m data set and MPII data set were used as the basis for testing. The results show HIGHLIGHTS• This paper addresses the problem that it is difficult to mine and extract the potential features of human motion posture feature vector.• The posture compensation function is used to compensate the error part to ensure the accuracy of posture estimation results• The posture compensation function is used to correct and compensate the estimation results and improve the reliability of the estimation results.

show abstract

“…This gives us the chance to investigate the networks from different perspectives. Exemplar applications of this property include the Conceptor-based post-processing of word vectors in [28] and the multi-label classification in [29]. In Conceptor-CAM, we will use it for converting the pseudo-negative evidences to pseudo-positive evidences using NOT operation.…”

Section: B Conceptor Learningmentioning

confidence: 99%

Conceptor Learning for Class Activation Mapping

Qian¹,

Yang²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs). The saliency maps are conventionally generated by fusing the channels of the target feature map using a weighted average scheme. It is a weak model for the inter-channel relation, in the sense that it only models the relation among channels in a contrastive way (i.e., channels that play key roles in the prediction are given higher weights for them to stand out in the fusion). The collaborative relation, which makes the channels work together to provide cross reference, has been ignored. Furthermore, the model has neglected the intra-channel relation thoroughly. In this paper, we address this problem by introducing Conceptor learning into CAM generation. Conceptor leaning has been originally proposed to model the patterns of state changes in recurrent neural networks (RNNs). By relaxing the dependency of Conceptor learning to RNNs, we make Conceptor-CAM not only generalizable to more DNN architectures but also able to learn both the inter-and intra-channel relations for better saliency map generation. Moreover, we have enabled the use of Boolean operations to combine the positive and pseudo-negative evidences, which has made the CAM inference more robust and comprehensive. The effectiveness of Conceptor-CAM has been validated with both formal verifications and experiments on the dataset of the largest scale in literature. The experimental results show that Conceptor-CAM is compatible with and can bring significant improvement to all well recognized CAM-based methods, and has outperformed the state-of-the-art methods by 43.14% ∼ 72.79% (88.39% ∼ 168.15%) on ILSVRC2012 in Average Increase (Drop), 15.42% ∼ 42.55% (47.09% ∼ 372.09%) on VOC, and 17.43% ∼ 31.32% (47.54% ∼ 206.45%) on COCO, respectively.

show abstract

Single-label and multi-label conceptor classifiers in pre-trained neural networks

Cited by 6 publications

References 25 publications

A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

Estimation of Human Motion Posture Using Multi-labeling Transfer Learning

Conceptor Learning for Class Activation Mapping

Contact Info

Product

Resources

About