Yu Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yu Ren has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Yang Cong
South China University of Technology
6 shared publications - Gan Sun
South China University of Technology
3 shared publications - Jiahua Dong
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
2 shared publications - Wei Cong
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2 shared publications - Bingtao Ma
Hangzhou Dianzi University, Hangzhou, China
1 shared publication - Chunmei Li
College of Animal Science & Technology, Nanjing Agricultural University, Nanjing 210095, China
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (11) , 13565-13572
SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (11) , 13565-13572
SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (3) , 1149-1162
Generalizable Multistage Assembly via One-Shot Category-Level Demonstration
Imitation learning offers a flexible approach for robot skill acquisition, enabling robots to learn complex tasks directly from demonstrations. However, most existing methods require a large number of demonstrations, whereas humans typically only need one or a few demonstrations. This discrepancy results in significant time consumption for data collection. Furthermore, these methods often assume that test scenarios will always be identical to the demonstration, which can lead to substantial performance degradation when facing novel scenarios, such as manipulating objects from the same category but with different shapes and sizes, or encountering object collisions during manipulation. To address these challenges, we propose a generalized multistage manipulation network for category-level robot assembly tasks. This network allows a robot to learn a multistage screw–nut assembly task from a single demonstration and generalize to new object instances with varying shapes and sizes. Specifically, the network uses category-level pose estimation to extract manipulation trajectories from the demonstration and applies manipulation-pose generalization to transfer these trajectories to novel instances. In addition, real-time action correction adjusts the trajectory based on real-time force feedback, enabling the robot to adapt to unexpected collisions during execution. We validate our method through experiments in both simulation and real-world environments, verifying its effectiveness and flexibility.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (3) , 1149-1162
Generalizable Multistage Assembly via One-Shot Category-Level Demonstration
Imitation learning offers a flexible approach for robot skill acquisition, enabling robots to learn complex tasks directly from demonstrations. However, most existing methods require a large number of demonstrations, whereas humans typically only need one or a few demonstrations. This discrepancy results in significant time consumption for data collection. Furthermore, these methods often assume that test scenarios will always be identical to the demonstration, which can lead to substantial performance degradation when facing novel scenarios, such as manipulating objects from the same category but with different shapes and sizes, or encountering object collisions during manipulation. To address these challenges, we propose a generalized multistage manipulation network for category-level robot assembly tasks. This network allows a robot to learn a multistage screw–nut assembly task from a single demonstration and generalize to new object instances with varying shapes and sizes. Specifically, the network uses category-level pose estimation to extract manipulation trajectories from the demonstration and applies manipulation-pose generalization to transfer these trajectories to novel instances. In addition, real-time action correction adjusts the trajectory based on real-time force feedback, enabling the robot to adapt to unexpected collisions during execution. We validate our method through experiments in both simulation and real-world environments, verifying its effectiveness and flexibility.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34, 4566-4579
Lightweight Class Incremental Semantic Segmentation Without Catastrophic Forgetting
Class incremental semantic segmentation (CISS) aims to progressively segment newly introduced classes while preserving the memory of previously learned ones. Traditional CISS methods directly employ advanced semantic segmentation models (e.g., Deeplab-v3) as continual learners. However, these methods require substantial computational and memory resources, limiting their deployment on edge devices. In this paper, we propose a Lightweight Class Incremental Semantic Segmentation (LISS) model tailored for resource-constrained scenarios. Specifically, we design an automatic knowledge-preservation pruning strategy based on the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which automatically compresses the CISS model by searching for global penalty coefficients. Nonetheless, reducing model parameters exacerbates catastrophic forgetting during incremental learning. To mitigate this challenge, we develop a clustering-based pseudo labels generator to obtain high-quality pseudo labels by considering the feature space structure of old classes. It adjusts predicted probabilities from the old model according to the feature proximity to nearest sub-cluster centers for each class. Additionally, we introduce a customized soft labels module that distills the semantic relationships between classes separately. It decomposes soft labels into target probabilities, background probabilities, and other probabilities, thereby maintaining knowledge of previously learned classes in a fine-grained manner. Extensive experiments on two benchmark datasets demonstrate that our LISS model outperforms state-of-the-art approaches in both effectiveness and efficiency.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34, 4566-4579
Lightweight Class Incremental Semantic Segmentation Without Catastrophic Forgetting
Class incremental semantic segmentation (CISS) aims to progressively segment newly introduced classes while preserving the memory of previously learned ones. Traditional CISS methods directly employ advanced semantic segmentation models (e.g., Deeplab-v3) as continual learners. However, these methods require substantial computational and memory resources, limiting their deployment on edge devices. In this paper, we propose a Lightweight Class Incremental Semantic Segmentation (LISS) model tailored for resource-constrained scenarios. Specifically, we design an automatic knowledge-preservation pruning strategy based on the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which automatically compresses the CISS model by searching for global penalty coefficients. Nonetheless, reducing model parameters exacerbates catastrophic forgetting during incremental learning. To mitigate this challenge, we develop a clustering-based pseudo labels generator to obtain high-quality pseudo labels by considering the feature space structure of old classes. It adjusts predicted probabilities from the old model according to the feature proximity to nearest sub-cluster centers for each class. Additionally, we introduce a customized soft labels module that distills the semantic relationships between classes separately. It decomposes soft labels into target probabilities, background probabilities, and other probabilities, thereby maintaining knowledge of previously learned classes in a fine-grained manner. Extensive experiments on two benchmark datasets demonstrate that our LISS model outperforms state-of-the-art approaches in both effectiveness and efficiency.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (4) , 2235-2248
IOSL: Incremental Open Set Learning
Class incremental learning (CIL) has drawn wide attention in academic researches. However, most existing methods cannot be applied to some practical scenarios in which unknown classes occur during the inference stage. To solve this problem, we target a more challenging and realistic setting: Incremental Open Set Learning (IOSL), which needs to reject unknown classes from test data while incrementally learning new classes. IOSL has two coupled key challenges: 1) overcoming the catastrophic forgetting of old classes when learning new classes incrementally due to the rarity of old training samples, and 2) minimizing the empirical classification risk on known classes and the open space risk on unknown classes. To address these challenges, we propose an incremental open-set learning method with a “future-look” ability. This ability reserves embedding space for incrementally arriving new classes and potential unknown classes simultaneously to alleviate the catastrophic forgetting indirectly and recognize unknown classes well. Specifically, a normalized prototype learning strategy is designed to minimize the empirical classification risk and implicitly reserve some space. Moreover, we design an extra classes synthesizing module to explicitly reserve more suitable space. This further minimizes the empirical classification risk while reducing the open space risk. Furthermore, we develop an adaptive metric learning loss to mitigate the class imbalance between old and new classes, which focuses on exploiting exemplars fully and selects an adaptive margin for pairs of old and new classes. Extensive experiments on representative classification datasets validate the superiority of our method.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (4) , 2235-2248
IOSL: Incremental Open Set Learning
Class incremental learning (CIL) has drawn wide attention in academic researches. However, most existing methods cannot be applied to some practical scenarios in which unknown classes occur during the inference stage. To solve this problem, we target a more challenging and realistic setting: Incremental Open Set Learning (IOSL), which needs to reject unknown classes from test data while incrementally learning new classes. IOSL has two coupled key challenges: 1) overcoming the catastrophic forgetting of old classes when learning new classes incrementally due to the rarity of old training samples, and 2) minimizing the empirical classification risk on known classes and the open space risk on unknown classes. To address these challenges, we propose an incremental open-set learning method with a “future-look” ability. This ability reserves embedding space for incrementally arriving new classes and potential unknown classes simultaneously to alleviate the catastrophic forgetting indirectly and recognize unknown classes well. Specifically, a normalized prototype learning strategy is designed to minimize the empirical classification risk and implicitly reserve some space. Moreover, we design an extra classes synthesizing module to explicitly reserve more suitable space. This further minimizes the empirical classification risk while reducing the open space risk. Furthermore, we develop an adaptive metric learning loss to mitigate the class imbalance between old and new classes, which focuses on exploiting exemplars fully and selects an adaptive margin for pairs of old and new classes. Extensive experiments on representative classification datasets validate the superiority of our method.
- 26 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (1) , 379-392
Uni3DA: Universal 3D Domain Adaptation for Object Recognition
Traditional 3D point cloud classification tasks focus on training a classifier in the closed-set scenario, where training and test data have the same label set and the same data distribution. In this work, we focus on a more challenging and realistic scenario in 3D point cloud classification task: universal domain adaptation (UniDA), where 1) data distributions for training and test data are different; and 2) for given label sets of training data and test data, they may have the shared classes and keep the private classes respectively, introducing an extra label set discrepancy. To solve UniDA problem, researchers have designed many methods based on 2D image datasets. However, due to the difficulty in capturing discriminative local geometric structures brought by the unordered and irregular 3D point cloud data, we cannot directly deploy the existing methods based on 2D image datasets to the 3D scenarios. To address UniDA in 3D scenarios, we develop a 3D universal domain adaptation framework, which consists of three modules: Self-Constructed Geometric (SCG) module, Local-to-Global Hypersphere Reasoning (LGHR) module and Self-Supervised Boundary Adaptation (SBA) module. SCG and LGHR generate the discriminative representation, which is used to acquire domain-invariant knowledge for training and test data. SBA is designed to automatically recognize whether a given label is from the shared label set or private label set, and adapts training and test data from the shared label set. To our best knowledge, this work is the first exploration of UniDA for 3D scenarios. Extensive experiments on public 3D point cloud datasets verify that the proposed method outperforms the existing UniDA methods.
- 26 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (1) , 379-392
Uni3DA: Universal 3D Domain Adaptation for Object Recognition
Traditional 3D point cloud classification tasks focus on training a classifier in the closed-set scenario, where training and test data have the same label set and the same data distribution. In this work, we focus on a more challenging and realistic scenario in 3D point cloud classification task: universal domain adaptation (UniDA), where 1) data distributions for training and test data are different; and 2) for given label sets of training data and test data, they may have the shared classes and keep the private classes respectively, introducing an extra label set discrepancy. To solve UniDA problem, researchers have designed many methods based on 2D image datasets. However, due to the difficulty in capturing discriminative local geometric structures brought by the unordered and irregular 3D point cloud data, we cannot directly deploy the existing methods based on 2D image datasets to the 3D scenarios. To address UniDA in 3D scenarios, we develop a 3D universal domain adaptation framework, which consists of three modules: Self-Constructed Geometric (SCG) module, Local-to-Global Hypersphere Reasoning (LGHR) module and Self-Supervised Boundary Adaptation (SBA) module. SCG and LGHR generate the discriminative representation, which is used to acquire domain-invariant knowledge for training and test data. SBA is designed to automatically recognize whether a given label is from the shared label set or private label set, and adapts training and test data from the shared label set. To our best knowledge, this work is the first exploration of UniDA for 3D scenarios. Extensive experiments on public 3D point cloud datasets verify that the proposed method outperforms the existing UniDA methods.
- Open Access
- 1 January 2021
- Published by Japan Poultry Science Association in The Journal of Poultry Science
- Vol. 58 (3) , 163-170
L-Leucine In Ovo Administration Causes Growth Retardation and Modifies Specific Amino Acid Metabolism in Broiler Embryos
L-Leucine (L-Leu) in ovo administration was demonstrated to afford thermotolerance and a modified amino acids metabolism in post-hatched broiler chicks under heat stress. This study aimed to investigate the changes in embryonic growth and amino acid metabolism after in ovo injection of L-Leu. Fertilized broiler eggs were subjected to in ovo injection of sterile water or L-Leu on embryonic day (ED) 7. The weight of embryos and yolk sacs were measured on ED 12, 14, 16, and 18. Plasma and livers were collected on ED 14 and 18 for free amino acid analysis. The weight and relative weight of embryos were significantly lowered by in ovo administration of L-Leu, but those of yolk sacs were not altered. Moreover, L-Leu in ovo injection significantly reduced the plasma proline concentration during embryogenesis and increased the plasma concentrations of tyrosine (Tyr) and lysine (Lys) in ED 18. Hepatic Lys concentration was also significantly increased by L-Leu in ovo injection. Interestingly, Leu concentrations in the plasma and liver were not affected by L-Leu administration. These results indicated that in ovo administered L-Leu was metabolized before ED 14 and affected embryonic growth and amino acid metabolism during embryogenesis.
- 1 January 2021
- Published by Japan Poultry Science Association in The Journal of Poultry Science
- Vol. 58 (3) , 163-170
Open AccessL-Leucine In Ovo Administration Causes Growth Retardation and Modifies Specific Amino Acid Metabolism in Broiler Embryos
L-Leucine (L-Leu) in ovo administration was demonstrated to afford thermotolerance and a modified amino acids metabolism in post-hatched broiler chicks under heat stress. This study aimed to investigate the changes in embryonic growth and amino acid metabolism after in ovo injection of L-Leu. Fertilized broiler eggs were subjected to in ovo injection of sterile water or L-Leu on embryonic day (ED) 7. The weight of embryos and yolk sacs were measured on ED 12, 14, 16, and 18. Plasma and livers were collected on ED 14 and 18 for free amino acid analysis. The weight and relative weight of embryos were significantly lowered by in ovo administration of L-Leu, but those of yolk sacs were not altered. Moreover, L-Leu in ovo injection significantly reduced the plasma proline concentration during embryogenesis and increased the plasma concentrations of tyrosine (Tyr) and lysine (Lys) in ED 18. Hepatic Lys concentration was also significantly increased by L-Leu in ovo injection. Interestingly, Leu concentrations in the plasma and liver were not affected by L-Leu administration. These results indicated that in ovo administered L-Leu was metabolized before ED 14 and affected embryonic growth and amino acid metabolism during embryogenesis.