Relative Distribution Entropy Loss Function in CNN Image Retrieval

Li, Pingping; Shi, Lida; Zhang, Miao; Jin, Baixin; Zhou, Qiuzhan

doi:10.3390/e22030321

Cited by 4 publications

(2 citation statements)

References 46 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, the similarity between two images has been measured by computing the Euclidean distance between their corresponding feature representations [40]. This method of similarity calculation is convenient and widely used in various domains such as image retrieval [40], [41], semantic labeling [42], face recognition [43], [44], motion capture [45], clustering algorithms [46], [47], and others, owing to its effectiveness and ease of computation. In the last few years, scholars have introduced more sophisticated techniques for evaluating image similarity, such as deep learning-based models [48].…”

Section: B: Euclidean Distance Evaluationmentioning

confidence: 99%

Pseudo 3D Pose Recognition Network

Xie

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Multi-view human pose recognition has been extensively studied in computer vision due to its significant practical implications. Nonetheless, it remains a challenging task to effectively integrate distinctive view-based features and perform thorough qualitative analysis and quantitative evaluations. In this paper, based on an innovative multi-view fusion module and a novel Mutable Scaling Shortcut Connection, a pseudo 3D pose recognition neural network was meticulously crafted. The proposed network framework comprises four modules: Front Residual Module, 3D Convolution Cross View Fusion Module, Rear Residual Module, and Detection Module. The Front Residual Module serves as the head module with incipient pose heatmaps extraction functionality, taking preprocessed images of various views as separate inputs. The 3D Convolution Cross View Fusion Module performs 3D convolution fusion for the heatmaps output from Front Residual Module of each view, enabling the heatmaps to benefit from each other consequently. The Rear Residual Module extracts deeper-level features, and ultimately the Detection Module performs pose classification and recognition. The proposed network can be trained end-to-end and was evaluated with a Self-Built Multi-View pose recognition dataset. Analytical and evaluation approaches were used to explain the contributory effects of the 3D Convolution Cross View Fusion Module, which significantly improve recognition accuracy from approximately 70% to 91%-94% through Feature Aggregation, Strong Interaction Property among views, Sparsity Reduction, and Increasing Euclidean Distance.

show abstract

Section: B: Euclidean Distance Evaluationmentioning

confidence: 99%

Pseudo 3D Pose Recognition Network

Xie

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…where yˆis the output of loss function such as softmax or Euclidean loss E , (• •) [13] in neural network model with L layers. b i is the bias vector of dimension K i of each layer, and W i represents the weight matrix of dimension…”

Section: Factors Related To Neural Networkmentioning

confidence: 99%

Influence factors of the accuracy of monocular vision pose estimation for spacecraft based on neural network

Zhao¹,

Ye²,

Guo³

et al. 2022

Eng. Res. Express

View full text Add to dashboard Cite

Accurate acquisition of spacecraft pose information is a key step in tasks such as space debris removal, rendezvous and docking, and on-orbit maintenance. The application of neural network has deepened for aerospace measurement and control. Studying the parameters’ influence and degree of imaging and neural network on the accuracy of spacecraft pose estimation is necessary and urgent, but there is still little research in related fields. Approximate Bayesian inference in the depth Gaussian process is utilized in this paper to explore above problems, and systematic verification experiments are carried based on the general neural network and spacecraft pose estimation data set. The verification results depict that the estimation errors of position and attitude can be both effectively reduced by selecting a camera whose radial distortion error is less than 240%. Selecting a camera with focal ratio error less than 2.0% can effectively reduce the position estimation error. Selecting a camera whose principal point error is less than 1.0% can effectively improve the accuracy of attitude estimation. The suppression of tangential distortion error does not significantly improve the estimation accuracy of both position and attitude. Parameters about weighted attenuation factor, the number of network layers and characteristic channels of neural network are all sensitive to the accuracy of pose estimation of spacecraft within a specific range. An excellent balance can be achieved between the estimation accuracy and computational overhead when the weight attenuation factor is set between 0.01 and 0.1, and the number of network layers and characteristic channels are set separately between 20~40 and 70~90. It can reach the accuracy of the traditional pose estimation algorithm, and has better processing time stability in real ground test system by using the network architecture of ResNet34 with weight attenuation factor of 0.01, characteristic channels of 90.

show abstract

Applying image registration algorithm combined with CNN model to video image stitching

Cao

2021

J Supercomput

View full text Add to dashboard Cite

Relative Distribution Entropy Loss Function in CNN Image Retrieval

Cited by 4 publications

References 46 publications

Pseudo 3D Pose Recognition Network

Pseudo 3D Pose Recognition Network

Influence factors of the accuracy of monocular vision pose estimation for spacecraft based on neural network

Applying image registration algorithm combined with CNN model to video image stitching

Contact Info

Product

Resources

About