Yaomin Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yaomin Huang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Chaomin Shen
East China Normal University, Shanghai, China
5 shared publications - Faming Fang
School of Computer Science and Technology, East China Normal University, Shanghai, China
3 shared publications - Guixu Zhang
East China Normal University, Shanghai, China
3 shared publications - Feifei Feng
Midea Group, Shanghai, China
2 shared publications - Jian Tang
Midea Group, Shanghai, China
2 shared publications - Zaomin Yan
East China Normal University
2 shared publications
Latest Publications
- 29 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 350
Eliciting CLIP’s intrinsic attribute knowledge through a dual-cache guided mechanism for class-incremental learning
- 29 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 350
Eliciting CLIP’s intrinsic attribute knowledge through a dual-cache guided mechanism for class-incremental learning
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4543-4552
Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation
Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a teacher-oriented paradigm that imposes the task of learning the teacher's complex knowledge onto the student network. However, significant disparities in model capacity and architectural design hinder the student's comprehension of the complex knowledge imparted by the teacher, resulting in sub-optimal performance. This paper introduces a novel perspective emphasizing student-oriented and refining the teacher's knowledge to better align with the student's needs, thereby improving knowledge transfer effectiveness. Specifically, we present the Student-Oriented Knowledge Distillation (SoKD), which incorporates a learnable feature augmentation strategy during training to refine the teacher's knowledge of the student dynamically. Furthermore, we deploy the Distinctive Area Detection Module (DAM) to identify areas of mutual interest between the teacher and student, concentrating knowledge transfer within these critical areas to avoid transferring irrelevant information. This customized module ensures a more focused and effective knowledge distillation process. Our approach, functioning as a plug-in, could be integrated with various knowledge distillation methods. Extensive experimental results demonstrate the efficacy and generalizability of our method.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4543-4552
Open AccessStudent-Oriented Teacher Knowledge Refinement for Knowledge Distillation
Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a teacher-oriented paradigm that imposes the task of learning the teacher's complex knowledge onto the student network. However, significant disparities in model capacity and architectural design hinder the student's comprehension of the complex knowledge imparted by the teacher, resulting in sub-optimal performance. This paper introduces a novel perspective emphasizing student-oriented and refining the teacher's knowledge to better align with the student's needs, thereby improving knowledge transfer effectiveness. Specifically, we present the Student-Oriented Knowledge Distillation (SoKD), which incorporates a learnable feature augmentation strategy during training to refine the teacher's knowledge of the student dynamically. Furthermore, we deploy the Distinctive Area Detection Module (DAM) to identify areas of mutual interest between the teacher and student, concentrating knowledge transfer within these critical areas to avoid transferring irrelevant information. This customized module ensures a more focused and effective knowledge distillation process. Our approach, functioning as a plug-in, could be integrated with various knowledge distillation methods. Extensive experimental results demonstrate the efficacy and generalizability of our method.
- 25 October 2024
- Published by Springer Nature
- p. 58-74
Harmonizing Knowledge Transfer in Neural Network with Unified Distillation
- 25 October 2024
- Published by Springer Nature
- p. 58-74
Harmonizing Knowledge Transfer in Neural Network with Unified Distillation
- Open Access
Harmonizing knowledge Transfer in Neural Network with Unified Distillation
Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories emerge within KD methods: feature-based, focusing on intermediate layers' features, and logits-based, targeting the final layer's logits. This paper introduces a novel perspective by leveraging diverse knowledge sources within a unified KD framework. Specifically, we aggregate features from intermediate layers into a comprehensive representation, effectively gathering semantic information from different stages and scales. Subsequently, we predict the distribution parameters from this representation. These steps transform knowledge from the intermediate layers into corresponding distributive forms, thereby allowing for knowledge distillation through a unified distribution constraint at different stages of the network, ensuring the comprehensiveness and coherence of knowledge transfer. Numerous experiments were conducted to validate the effectiveness of the proposed method.
Open AccessHarmonizing knowledge Transfer in Neural Network with Unified Distillation
Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories emerge within KD methods: feature-based, focusing on intermediate layers' features, and logits-based, targeting the final layer's logits. This paper introduces a novel perspective by leveraging diverse knowledge sources within a unified KD framework. Specifically, we aggregate features from intermediate layers into a comprehensive representation, effectively gathering semantic information from different stages and scales. Subsequently, we predict the distribution parameters from this representation. These steps transform knowledge from the intermediate layers into corresponding distributive forms, thereby allowing for knowledge distillation through a unified distribution constraint at different stages of the network, ensuring the comprehensiveness and coherence of knowledge transfer. Numerous experiments were conducted to validate the effectiveness of the proposed method.
- Open Access
CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network
In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data performs very well for real robots.
Open AccessCMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network
In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data performs very well for real robots.
- 6 November 2022
- Published by Springer Nature
- p. 684-700
Label-Guided Auxiliary Training Improves 3D Object Detector
- 6 November 2022
- Published by Springer Nature
- p. 684-700
Label-Guided Auxiliary Training Improves 3D Object Detector