Papers › Object-Centric Multi-Task Learning for Human Instances

Object-Centric Multi-Task Learning for Human Instances

13 Mar 2023arXiv:2303.06800archive 2025-07-28

Hyeongseok Son, Sangil Jung, Solae Lee, Seongeun Kim, Seung-In Park, ByungIn Yoo

Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation. Although much effort has been put into individual tasks, multi-task learning for these three tasks has been rarely studied. In this paper, we explore a compact multi-task network architecture that maximally shares the parameters of the multiple tasks via object-centric learning. To this end, we propose a novel query design to encode the human instance information effectively, called human-centric query (HCQ). HCQ enables for the query to learn explicit and structural information of human as well such as keypoints. Besides, we utilize HCQ in prediction heads of the target tasks directly and also interweave HCQ with the deformable attention in Transformer decoders to exploit a well-learned object-centric representation. Experimental results show that the proposed multi-task network achieves comparable accuracy to state-of-the-art task-specific models in human detection, segmentation, and pose estimation task, while it consumes less computational costs.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Human Detection Human Instance Segmentation Multi-Task Learning Object Pose Estimation Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Human Instance Segmentation	OCHuman	Mask2Former	AP	27.8	#7 of 18	Archive leaderboard	report
Human Instance Segmentation	OCHuman	HCQNet	AP	27.3	#8 of 18	Archive leaderboard	report
Human Instance Segmentation	OCHuman	BaseNet-DPS	AP	25.5	#12 of 18	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections