CDGNet: Class Distribution Guided Network for Human Parsing

Liu, Kunliang; Choi, Ouk; Wang, Jianming; Hwang, Wonjun

doi:10.1109/cvpr52688.2022.00443

Cited by 29 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the above methods, there are several other deep learning methods for human parsing, such as the following: CDGNet [38] simplifies the complex spatial human parsing problem into the horizontal and vertical positions of human parts individually. Accordingly, the method builds the class distribution labels in the horizontal and vertical directions as new supervision signals from the original label of human parsing.…”

Section: F Other Modelsmentioning

confidence: 99%

Deep Learning for Human Parsing: A Survey

Zhang¹,

Zhu²,

Tang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Human parsing is a key topic in image processing with many applications, such as surveillance analysis, humanrobot interaction, person search, and clothing category classification, among many others. Recently, due to the success of deep learning in computer vision, there are a number of works aimed at developing human parsing algorithms using deep learning models. As methods have been proposed, a comprehensive survey of this topic is of great importance. In this survey, we provide an analysis of state-of-the-art human parsing methods, covering a broad spectrum of pioneering works for semantic human parsing. We introduce five insightful categories: (1) structuredriven architectures exploit the relationship of different human parts and the inherent hierarchical structure of a human body, (2) graph-based networks capture the global information to achieve an efficient and complete human body analysis, (3) context-aware networks explore useful contexts across all pixel to characterize a pixel of the corresponding class, (4) LSTM-based methods can combine short-distance and long-distance spatial dependencies to better exploit abundant local and global contexts, and (5) combined auxiliary information approaches use related tasks or supervision to improve network performance. We also discuss the advantages/disadvantages of the methods in each category and the relationships between methods in different categories, examine the most widely used datasets, report performances, and discuss promising future research directions in this area.

show abstract

Section: F Other Modelsmentioning

confidence: 99%

Deep Learning for Human Parsing: A Survey

Zhang¹,

Zhu²,

Tang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We transitioned the principal network structure of our student model to ResNet18 [3], while the teacher model, CDGNet [2], retained ResNet101 [3] as its primary network. This modification resulted in a notable disparity between the student and teacher models.…”

Section: Intra-class and Inter-class Relationship-based Knowledge Dis...mentioning

confidence: 99%

“…(2) We incorporated a spatial attention mechanism into the decoder, fusing it with the shallow feature module, enhancing our model's efficiency. (3) We utilized KD techniques with CDGNet [2] serving as our teacher network and implemented a distillation method better equipped to handle the significant discrepancies between the teacher and student models, thereby mitigating potential accuracy losses inherent in traditional distillation methods.…”

Section: Introductionmentioning

confidence: 99%

“…The addition of a spatial attention mechanism and a shallow feature module enhanced efficiency. By using CDGNet [2] as a teacher network, we applied a flexible knowledge distillation (KD) technique to preserve accuracy, even with considerable architecture differences. This method distilled intra‐class and inter‐class relationships from model outputs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Class relationship‐based knowledge distillation for efficient human parsing

Lang

Liu

Wang

et al. 2023

Electronics Letters

Self Cite

View full text Add to dashboard Cite

In computer vision, human parsing is challenging due to its demand for accurate human region location and semantic partitioning. This dense prediction task needs powerful computation and high‐precision models. To enable real‐time parsing on resource‐limited devices, the authors introduced a lightweight model using ResNet18 as a core network . The authors simplified the pyramid module, improving context clarity and reducing complexity. The authors integrated a spatial attention fusion strategy to counter precision loss in the light‐weighting process. Traditional models, despite their segmentation precision, are limited by their computational complexity and extensive parameters. The authors implemented knowledge distillation (KD) techniques to enhance the authors’ lightweight network's accuracy. Traditional methods can fail to learn useful knowledge with significant network differences. Hence, the authors used a novel distillation approach based on inter‐class and intra‐class relations in prediction outcomes, noticeably improving parsing accuracy. The authors’ experiments on the Look into Person (LIP) dataset show that their lightweight model significantly reduces parameters while maintaining parsing precision and enhancing inference speed.

show abstract

“…3D data is used in many different fields, including autonomous driving, robotics, remote sensing, and more [5,12,14,17,47]. Point cloud has a very uniform structure, which avoids the irregularity and complexity of composition.…”

Section: Introductionmentioning

confidence: 99%

ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer

Li¹,

Gao²,

Tan³

et al. 2023

Preprint

View full text Add to dashboard Cite

Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus make these proxies more suitable for subsequent coarse-to-fine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed. Code is available at https://github. com/I2-Multimedia-Lab/ProxyFormer.

show abstract

CDGNet: Class Distribution Guided Network for Human Parsing

Cited by 29 publications

References 24 publications

Deep Learning for Human Parsing: A Survey

Deep Learning for Human Parsing: A Survey

Class relationship‐based knowledge distillation for efficient human parsing

ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer

Contact Info

Product

Resources

About