Semantic-spatial fusion network for human parsing

Zhang, Xiaomei; Chen, Yingying; Zhu, Bingke; Wang, Jinqiao; Tang, Ming

doi:10.1016/j.neucom.2020.03.096

Cited by 13 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [20] innovatively proposed a fusion framework (SSFNet), which effectively mitigates the gap between features by means of a semantic modulation model and a resolutionaware model. There are still many deep learning-based models that are applied for different tasks.…”

Section: Related Workmentioning

confidence: 99%

Underwater Incomplete Target Recognition Network via Generating Feature Module

Shen

Jia

Cai

2023

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

A complex and changeable underwater archaeological environment leads to the lack of target features in the collected images, affecting the accuracy of target detection. Meanwhile, the difficulty in obtaining underwater archaeological images leads to less training data, resulting in poor generalization performance of the recognition algorithm. For these practical issues, we propose an underwater incomplete target recognition network via generating feature module (UITRNet). Specifically, for targets that lack features, features are generated by dual discriminators and generators to improve target detection accuracy. Then, multilayer features are fused to extract regions of interest. Finally, supervised contrastive learning is introduced into few-shot learning to improve the intraclass similarity and interclass distance of the target and enhance the generalization of the algorithm. The UIFI dataset is produced to verify the effectiveness of the algorithm in this paper. The experimental results show that the mean average precision (mAP) of our algorithm was improved by 0.86% and 1.29% under insufficient light and semiburied interference, respectively. The mAP for ship identification reached the highest level under all four sets of experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Underwater Incomplete Target Recognition Network via Generating Feature Module

Shen

Jia

Cai

2023

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…For the transformer, we adopt the slot attention [22] with learnable slots as encoder and use MLP as decoder, where the iteration of slot attention is set to 3. We extract the foreground mask by SSFNet [43] to concentrate on the part discovery. For fair comparisons, we do the same operation for other unsupervised face segmentation methods that required foreground masks.…”

Section: Implementation Detailsmentioning

confidence: 99%

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

Yu¹,

Zhu²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

as the face hierarchy is progressively built and refined, the part capsules adaptively encode the face parts with semantic consistency. HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand homologous objects without human intervention. Besides, HP-Capsule gives unsupervised face segmentation results by the covered regions of part capsules, enabling qualitative and quantitative evaluation. Experiments on BP4D and Multi-PIE datasets show the effectiveness of our method.

show abstract

“…For the problems of underwater environment interference and algorithm real time, Cai et al [14] proposed a collaborative multi-AUV target recognition method based on migration reinforcement learning. Zhang et al [15] proposed a semantic spatial fusion network (SSFNet) to bridge the gap between low-level and high-level features. Moniruzzaman et al [16] proposed a Faster R-CNN algorithm using the Inception V2 network.…”

Section: Related Workmentioning

confidence: 99%

Underwater Distortion Target Recognition Network (UDTRNet) via Enhanced Image Features

Cai

Chen

Chai

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

It is difficult for the autonomous underwater vehicle (AUV) to recognize targets similar to the environment in lacking data labels. Moreover, the complex underwater environment and the refraction of light cause the AUV to be unable to extract the complete significant features of the target. In response to the above problems, this paper proposes an underwater distortion target recognition network (UDTRNet) that can enhance image features. Firstly, this paper extracts the significant features of the image by minimizing the info noise contrastive estimation (InfoNCE) loss. Secondly, this paper constructs the dynamic correlation matrix to capture the spatial semantic relationship of the target and uses the matrix to extract spatial semantic features. Finally, this paper fuses the significant features and spatial semantic features of the target and trains the target recognition model through cross-entropy loss. The experimental results show that the mean average precision (mAP) of the algorithm in this paper increases by 1.52% in recognizing underwater blurred images.

show abstract

Semantic-spatial fusion network for human parsing

Cited by 13 publications

References 7 publications

Underwater Incomplete Target Recognition Network via Generating Feature Module

Underwater Incomplete Target Recognition Network via Generating Feature Module

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

Underwater Distortion Target Recognition Network (UDTRNet) via Enhanced Image Features

Contact Info

Product

Resources

About