Junxi Chen
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
Junxi Chen has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Ruixuan Wang
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
3 shared publications Guangxing Wu
2 shared publications- Wentao Zhang
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
2 shared publications - Guangxing Wu
Sun Yat-Sen University, China
1 shared publication - Hongxiang Li
The Hong Kong University of Science and Technology, Hong Kong, Hong Kong
1 shared publication Jianhua Feng
Institute of Microelectronics, Peking University, Beijing, 100871, P.R. China
1 shared publication
Latest Publications
- 14 July 2026
- Published by Elsevier in Neurocomputing
- Vol. 701
Mixture of knowledge from multiple pre-trained foundation models for few-shot recognition
- 14 July 2026
- Published by Elsevier in Neurocomputing
- Vol. 701
Mixture of knowledge from multiple pre-trained foundation models for few-shot recognition
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 7143-7154
DAT: Dual-Branch Adapter-Tuning for Few-Shot Recognition
Parameter-Efficient Fine-Tuning methods based on vision-language models (such as CLIP) for few-shot learning have recently received considerable attention. However, previous works only fine-tune either the image or text branch, breaking the alignment of the original two branches, meanwhile fine-tuning both branches of the CLIP would inevitably introduce more trainable parameters and likely cause more severe over-fitting due to the limited training data. In this study, we propose a novel Dual-branch Adapter-Tuning framework (DAT), which collaboratively trains the visual adapter and textual adapter added to the two branches of the original CLIP with multiple consistency constraints. By effectively utilizing the semantically detailed class-specific prompts and outputs of the original CLIP to guide the fine-tuning of both branches, our method gains exceptional adaptation ability to the downstream few-shot learning tasks and alleviates the over-fitting issue, meanwhile maximally preserving the generalization ability of the original CLIP model. Our proposed framework has achieved superior performance on diverse datasets under various few-shot learning settings compared to the existing approaches. The source code is available at https://github.com/SandyXi/DAT.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 7143-7154
DAT: Dual-Branch Adapter-Tuning for Few-Shot Recognition
Parameter-Efficient Fine-Tuning methods based on vision-language models (such as CLIP) for few-shot learning have recently received considerable attention. However, previous works only fine-tune either the image or text branch, breaking the alignment of the original two branches, meanwhile fine-tuning both branches of the CLIP would inevitably introduce more trainable parameters and likely cause more severe over-fitting due to the limited training data. In this study, we propose a novel Dual-branch Adapter-Tuning framework (DAT), which collaboratively trains the visual adapter and textual adapter added to the two branches of the original CLIP with multiple consistency constraints. By effectively utilizing the semantically detailed class-specific prompts and outputs of the original CLIP to guide the fine-tuning of both branches, our method gains exceptional adaptation ability to the downstream few-shot learning tasks and alleviates the over-fitting issue, meanwhile maximally preserving the generalization ability of the original CLIP model. Our proposed framework has achieved superior performance on diverse datasets under various few-shot learning settings compared to the existing approaches. The source code is available at https://github.com/SandyXi/DAT.
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Feature Adaptation with CLIP for Few-shot Classification
Large Vision-Language models such as CLIP have demonstrated impressive capabilities in zero-shot recognition. To apply CLIP to few-shot classification tasks, several methods have been proposed based on CLIP, achieving significant improvements. However, these methods either insufficiently leverage CLIP’s prior knowledge during training or neglect the impact of feature adaptation. In this paper, we propose FAR, a novel approach that balances distribution-altered Feature Adaptation with pRior knowledge of CLIP to further improve the performance of CLIP in few-shot classification tasks. Firstly, we introduce an adapter that enhances the effectiveness of CLIP adaptation by amplifying the differences between the fine-tuned CLIP features and the original CLIP features. Secondly, we leverage the prior knowledge of CLIP to mitigate the risk of overfitting. Through this framework, a good trade-off between feature adaptation and preserving prior knowledge is achieved, enabling effective utilization of both components to enhance performance on downstream tasks. We evaluate our method on over 10 datasets for classification, and our approach consistently outperforms existing methods, demonstrating its effectiveness and robustness.
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessFeature Adaptation with CLIP for Few-shot Classification
Large Vision-Language models such as CLIP have demonstrated impressive capabilities in zero-shot recognition. To apply CLIP to few-shot classification tasks, several methods have been proposed based on CLIP, achieving significant improvements. However, these methods either insufficiently leverage CLIP’s prior knowledge during training or neglect the impact of feature adaptation. In this paper, we propose FAR, a novel approach that balances distribution-altered Feature Adaptation with pRior knowledge of CLIP to further improve the performance of CLIP in few-shot classification tasks. Firstly, we introduce an adapter that enhances the effectiveness of CLIP adaptation by amplifying the differences between the fine-tuned CLIP features and the original CLIP features. Secondly, we leverage the prior knowledge of CLIP to mitigate the risk of overfitting. Through this framework, a good trade-off between feature adaptation and preserving prior knowledge is achieved, enabling effective utilization of both components to enhance performance on downstream tasks. We evaluate our method on over 10 datasets for classification, and our approach consistently outperforms existing methods, demonstrating its effectiveness and robustness.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
A clock-feedthrough compensation technique for bootstrapped switch
This paper presents a clock-feedthrough compensation technique for bootstrapped switches. The proposed technique utilizes a dummy transistor to generate a reverse voltage, which compensates the input-dependent error caused by clock feedthrough effect of sampling switch. Simulation result shows the differential sampling error of bootstrapped switch reduces from 7.2mV to 1.4mV for the worst case, operating at 500MHz sampling speed in 55nm CMOS technology with a 300fF hold capacitor. The bootstrapped switch consumes 27uW power with only 1.5uW in compensation.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
A clock-feedthrough compensation technique for bootstrapped switch
This paper presents a clock-feedthrough compensation technique for bootstrapped switches. The proposed technique utilizes a dummy transistor to generate a reverse voltage, which compensates the input-dependent error caused by clock feedthrough effect of sampling switch. Simulation result shows the differential sampling error of bootstrapped switch reduces from 7.2mV to 1.4mV for the worst case, operating at 500MHz sampling speed in 55nm CMOS technology with a 300fF hold capacitor. The bootstrapped switch consumes 27uW power with only 1.5uW in compensation.