Self-Supervised Neural Aggregation Networks for Human Parsing

Zhao, Jian; Li, Jianshu; Nie, Xuecheng; Zhao, Fang; Chen, Yunpeng; Wang, Zhecan; Feng, Jiashi; Yan, Shuicheng

doi:10.1109/cvprw.2017.204

Cited by 73 publications

(39 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has 4,371 images in total (3,934 for training, and 437 for testing). Evaluation Metrics: For LIP, following its standard protocol [78], we report pixel accuracy, mean accuracy and mean Intersection-over-Union (mIoU). For PASCAL-Person-Part, following conventions [70,71,50], the performance is evaluated in terms of mIoU.…”

Section: Implementation Detailsmentioning

confidence: 99%

Learning Compositional Neural Information Fusion for Human Parsing

Wang

Zhang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

133

View full text Add to dashboard Cite

This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing. We formulate the approach as a neural information fusion framework. Our model assembles the information from three inference processes over the hierarchy: direct inference (directly predicting each part of a human body using image information), bottom-up inference (assembling knowledge from constituent parts), and top-down inference (leveraging context from parent nodes). The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively. In addition, the fusion of multi-source information is conditioned on the inputs, i.e., by estimating and considering the confidence of the sources. The whole model is end-to-end differentiable, explicitly modeling information flows and structures. Our approach is extensively evaluated on four popular datasets, outperforming the state-of-the-arts in all cases, with a fast processing speed of 23fps. Our code and results have been released to help ease future research in this direction. * Equal contribution. † Corresponding author: Yanwei Pang.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Learning Compositional Neural Information Fusion for Human Parsing

Wang

Zhang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

133

View full text Add to dashboard Cite

show abstract

“…In addition, global image‐level context is proposed to guarantee the coherence between pixel‐wise labelling and image‐label prediction. The end‐to‐end parsing network could effectively eliminate the error accumulation effect of the linear pipeline [10–14, 35]. Therefore, it achieves some state‐of‐the‐art performance on ATR dataset [10].…”

Section: Related Workmentioning

confidence: 99%

“…The multi‐scale operation is another effective way for the various image segmentation problems. Zhao et al [13] proposed an adaptive neural aggregation to fuse the multi‐scale features and achieved state‐of‐the‐art performance on LIP dataset. He and Yang [14] utilised InceptionNet and atrous spatial pyramid pooling structure to generate multi‐scale features and realised a real‐time parsing by pruning the network.…”

Section: Related Workmentioning

confidence: 99%

“…For example, providing the precise clothing patch could effectively exclude the interference from the background and increase the accuracy of clothing retrieval [6, 7]. Recent deep parsing methods either adopt a multi‐stage pipeline in which deep network serves as a feature extractor [8–10] or proposes an end‐to‐end parsing framework to generate the semantic labels directly [10–14]. These methods could effectively improve the parsing performance by optimising the parsing pipeline or adopting more prior information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Conditional progressive network for clothing parsing

Zhang

Luo

et al. 2019

IET Image Processing

View full text Add to dashboard Cite

“…Similarly, the authors of Reference [35] proposed to integrate parsing with optical flow estimation. The authors of Reference [36] incorporated a self-supervised joint loss to ensure the consistency between parsing and pose. However, the guidance from poses cannot improve borders.…”

Section: Related Workmentioning

confidence: 99%

A CNN Model for Human Parsing Based on Capacity Optimization

Jiang

Chi

2019

Applied Sciences

View full text Add to dashboard Cite

Although a state-of-the-art performance has been achieved in pixel-specific tasks, such as saliency prediction and depth estimation, convolutional neural networks (CNNs) still perform unsatisfactorily in human parsing where semantic information of detailed regions needs to be perceived under the influences of variations in viewpoints, poses, and occlusions. In this paper, we propose to improve the robustness of human parsing modules by introducing a depth-estimation module. A novel scheme is proposed for the integration of a depth-estimation module and a human-parsing module. The robustness of the overall model is improved with the automatically obtained depth labels. As another major concern, the computational efficiency is also discussed. Our proposed human parsing module with 24 layers can achieve a similar performance as the baseline CNN model with over 100 layers. The number of parameters in the overall model is less than that in the baseline model. Furthermore, we propose to reduce the computational burden by replacing a conventional CNN layer with a stack of simplified sub-layers to further reduce the overall number of trainable parameters. Experimental results show that the integration of two modules contributes to the improvement of human parsing without additional human labeling. The proposed model outperforms the benchmark solutions and the capacity of our model is better matched to the complexity of the task.

show abstract

Self-Supervised Neural Aggregation Networks for Human Parsing

Cited by 73 publications

References 19 publications

Learning Compositional Neural Information Fusion for Human Parsing

Learning Compositional Neural Information Fusion for Human Parsing

Conditional progressive network for clothing parsing

A CNN Model for Human Parsing Based on Capacity Optimization

Contact Info

Product

Resources

About