Jiaming Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiaming Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Junming Shao
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Wei Han
Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Zhili Qin
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2 shared publications - Christian Böhm
Ludwig-Maximilians-Universität München, Munich, Germany
1 shared publication - Hongyuan Liu
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Jinxia Guo
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6301-6310
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6301-6310
Open AccessThe Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
- 10 April 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 250, 123848
Rethinking few-shot class-incremental learning: A lazy learning baseline
- 10 April 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 250, 123848
Rethinking few-shot class-incremental learning: A lazy learning baseline
- 30 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (11) , 16762-16774
Synchronization-Inspired Interpretable Neural Networks
Synchronization is a ubiquitous phenomenon in nature that enables the orderly presentation of information. In the human brain, for instance, functional modules such as the visual, motor, and language cortices form through neuronal synchronization. Inspired by biological brains and previous neuroscience studies, we propose an interpretable neural network incorporating a synchronization mechanism. The basic idea is to constrain each neuron, such as a convolution filter, to capture a single semantic pattern while synchronizing similar neurons to facilitate the formation of interpretable functional modules. Specifically, we regularize the activation map of a neuron to surround its focus position of the activated pattern in a sample. Moreover, neurons locally interact with each other, and similar ones are synchronized together during the training phase adaptively. Such local aggregation preserves the globally distributed representation nature of the neural network model, enabling a reasonably interpretable representation. To analyze the neuron interpretability comprehensively, we introduce a series of novel evaluation metrics from multiple aspects. Qualitative and quantitative experiments demonstrate that the proposed method outperforms many state-of-the-art algorithms in terms of interpretability. The resulting synchronized functional modules show module consistency across data and semantic specificity within modules.
- 30 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (11) , 16762-16774
Synchronization-Inspired Interpretable Neural Networks
Synchronization is a ubiquitous phenomenon in nature that enables the orderly presentation of information. In the human brain, for instance, functional modules such as the visual, motor, and language cortices form through neuronal synchronization. Inspired by biological brains and previous neuroscience studies, we propose an interpretable neural network incorporating a synchronization mechanism. The basic idea is to constrain each neuron, such as a convolution filter, to capture a single semantic pattern while synchronizing similar neurons to facilitate the formation of interpretable functional modules. Specifically, we regularize the activation map of a neuron to surround its focus position of the activated pattern in a sample. Moreover, neurons locally interact with each other, and similar ones are synchronized together during the training phase adaptively. Such local aggregation preserves the globally distributed representation nature of the neural network model, enabling a reasonably interpretable representation. To analyze the neuron interpretability comprehensively, we introduce a series of novel evaluation metrics from multiple aspects. Qualitative and quantitative experiments demonstrate that the proposed method outperforms many state-of-the-art algorithms in terms of interpretability. The resulting synchronized functional modules show module consistency across data and semantic specificity within modules.