Learning Semantic Neural Tree for Human Parsing

Ji, Ruyi; Du, Dawei; Zhang, Libo; Wen, Longyin; Wu, Yicheng; Zhao, Chen; Huang, Feiyue; Lyu, Siwei

doi:10.1007/978-3-030-58601-0_13

Cited by 52 publications

(29 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates the importance of our multigranularity representation learning in instance-level parsing. Furthermore, our approach shows better overall performance than most top-down methods (e.g., SNT [24], P-RCNN [58], M-CE2P [42]), revealing our appealing performance. Compared to RP-RCNN [57], our approach only performs slightly worse in terms of instance-level metrics (e.g., AP p 50 ).…”

Section: Quantitative Resultsmentioning

confidence: 80%

“…As of to date, there exist two paradigms for instance-aware human parsing: top-down and bottom-up. Top-down approaches [31,58,42,24,57] typically locate human instance proposals first, and then parse each proposal in a fine-grained manner. In contrast, bottom-up human parsers [14,30,65] simultaneously perform pixel-wise instance-agnostic parsing and pixel grouping, inspired by existing bottom-up instance segmentation techniques.…”

Section: Related Workmentioning

confidence: 99%

“…Extensive experiments are conducted on three instanceaware human parsing datasets. Specifically, on MHP v2 [65], our model achieves an AP p 50 of 39.0, much better than current top-leading bottom-up method (i.e., NAN [65] of 25.1) and on par with best top-down parsers [24,57]. On DensePose-COCO [1] and PASCAL-Person-Part [53], our model also produces compelling performance.…”

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

Zhou

Yang

Liu

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

To address the challenging task of instance-aware human part parsing, a new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner. It is a compact, efficient and powerful framework that exploits structural information over different human granularities and eases the difficulty of person partitioning. Specifically, a dense-to-sparse projection field, which allows explicitly associating dense human semantics with sparse keypoints, is learnt and progressively improved over the network feature pyramid for robustness. Then, the difficult pixel grouping problem is cast as an easier, multiperson joint assembling task. By formulating joint association as maximum-weight bipartite matching, a differentiable solution is developed to exploit projected gradient descent and Dykstra's cyclic projection algorithm. This makes our method end-to-end trainable and allows back-propagating the grouping error to directly supervise multi-granularity human representation learning. This is distinguished from current bottom-up human parsers or pose estimators which require sophisticated post-processing or heuristic greedy algorithms. Experiments on three instance-aware human parsing datasets show that our model outperforms other bottom-up alternatives with much more efficient inference.

show abstract

Section: Quantitative Resultsmentioning

confidence: 80%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

Zhou

Yang

Liu

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…They can be divided into three main categories. Top-down two-stage methods require human-instance segmentation of the image as an additional input [19,20,21,4]. Their computation time highly depends on the number of people in the image.…”

Section: Introductionmentioning

confidence: 99%

Describe Me If You Can! Characterized Instance-Level Human Parsing

Loesch¹,

Audigier²

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Several computer vision applications such as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it localizes semantic attributes and body parts within a person. But how to characterize these attributes? To our knowledge, only some single-HP datasets describe attributes with some color, size and/or pattern characteristics. There is a lack of dataset for multi-HP in the wild with such characteristics. In this article, we propose the dataset CCIHP based on the multi-HP dataset CIHP, with 20 new labels covering these 3 kinds of characteristics. 1 In addition, we propose HPTR, a new bottom-up multi-task method based on transformers as a fast and scalable baseline. It is the fastest method of multi-HP state of the art while having precision comparable to the most precise bottom-up method. We hope this will encourage research for fast and accurate methods of precise human descriptions.

show abstract

“…Several works took advantage of human characteristics for achieving better performance in human parsing. Ji et al [19] designed a novel semantic neural tree to encode the physiological structure of the human body and achieved competitive results. Wang et al [31,32] exploited deep graph networks and hierarchical human structures to capture the relation information of human parts and obtained better performances.…”

Section: Introductionmentioning

confidence: 99%

CDGNet: Class Distribution Guided Network for Human Parsing

Liu¹,

Choi²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according to the classes. Since the human body comprises hierarchically structured parts, each body part of an image can have its sole position distribution characteristics. Probably, a human head is less likely to be under the feet, and arms are more likely to be near the torso. Inspired by this observation, we make instance class distributions by accumulating the original human parsing label in the horizontal and vertical directions, which can be utilized as supervision signals. Using these horizontal and vertical class distribution labels, the network is guided to exploit the intrinsic position distribution of each class. We combine two guided features to form a spatial guidance map, which is then superimposed onto the baseline network by multiplication and concatenation to distinguish the human parts precisely. We conducted extensive experiments to demonstrate the effectiveness and superiority of our method on three well-known benchmarks: LIP, ATR, and CIHP databases.

show abstract

Learning Semantic Neural Tree for Human Parsing

Cited by 52 publications

References 36 publications

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

Describe Me If You Can! Characterized Instance-Level Human Parsing

CDGNet: Class Distribution Guided Network for Human Parsing

Contact Info

Product

Resources

About