Siqi Zhang
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
Siqi Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Lu Zhang
Institute of Automation, Chinese Academy of Sciences
3 shared publications - Zhiyong Liu
Institute of Automation, Chinese Academy of Sciences
3 shared publications Guangsen Li
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication- Hangtao Feng
Chinese Academy of Sciences
1 shared publication Lu Zhang
1 shared publicationPengcheng Li
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- 24 September 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 163
Test-time adaptation for object detection via Dynamic Dual Teaching
- 24 September 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 163
Test-time adaptation for object detection via Dynamic Dual Teaching
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (1) , 1589-1601
Multi-Prototype Guided Source-Free Domain Adaptive Object Detection for Autonomous Driving
Source-free domain adaptive object detection (source-free DAOD) seeks to adapt a detector pre-trained on a source domain to an unlabeled target domain without requiring access to annotated source domain data. To address challenges posed by domain shifts, current source-free DAOD approaches mainly rely on the self-training paradigm, where pseudo labels are predicted and employed to fine-tune the detector on unlabeled target domain. However, these methods often encounter issues related to intra-class variation, resulting in category-specific biases and noisy pseudo labels. In response, we present an effective Multi-Prototype Guided source-free DAOD method, dubbed MPG, consisting of two key components: multi-prototype guided pseudo labeling (MPPL) and multi-prototype guided consistency regularization (MPCR) modules. In the MPPL module, we construct category-specific multiple prototypes to better represent the category with intra-class variations. Specifically, multiple prototypes with adaptive cluster centroids are introduced for each category to effectively capture the intra-class variations. Through the implementation of the proposed MPPL module, we derive more accurate pseudo labels by assessing the proximity of instance features to multiple category prototypes. In the MPCR module, we introduce multi-level consistency regularization, including prototype-based consistency and prediction consistency, which encourages the model to overlook style perturbations and learn domain-invariant representations. Extensive experiments on five public driving datasets demonstrate that MPG outperforms existing state-of-the-art methods, showcasing its effectiveness in adapting object detectors to target domains.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (1) , 1589-1601
Multi-Prototype Guided Source-Free Domain Adaptive Object Detection for Autonomous Driving
Source-free domain adaptive object detection (source-free DAOD) seeks to adapt a detector pre-trained on a source domain to an unlabeled target domain without requiring access to annotated source domain data. To address challenges posed by domain shifts, current source-free DAOD approaches mainly rely on the self-training paradigm, where pseudo labels are predicted and employed to fine-tune the detector on unlabeled target domain. However, these methods often encounter issues related to intra-class variation, resulting in category-specific biases and noisy pseudo labels. In response, we present an effective Multi-Prototype Guided source-free DAOD method, dubbed MPG, consisting of two key components: multi-prototype guided pseudo labeling (MPPL) and multi-prototype guided consistency regularization (MPCR) modules. In the MPPL module, we construct category-specific multiple prototypes to better represent the category with intra-class variations. Specifically, multiple prototypes with adaptive cluster centroids are introduced for each category to effectively capture the intra-class variations. Through the implementation of the proposed MPPL module, we derive more accurate pseudo labels by assessing the proximity of instance features to multiple category prototypes. In the MPCR module, we introduce multi-level consistency regularization, including prototype-based consistency and prediction consistency, which encourages the model to overlook style perturbations and learn domain-invariant representations. Extensive experiments on five public driving datasets demonstrate that MPG outperforms existing state-of-the-art methods, showcasing its effectiveness in adapting object detectors to target domains.
- 29 April 2023
- Published by Elsevier in Neurocomputing
- Vol. 542
Frequency-based pseudo-domain generation for domain generalizable object detection
- 29 April 2023
- Published by Elsevier in Neurocomputing
- Vol. 542
Frequency-based pseudo-domain generation for domain generalizable object detection
- 13 April 2023
- Published by Springer Nature
- p. 240-252
FIT: Frequency-Based Image Translation for Domain Adaptive Object Detection
- 13 April 2023
- Published by Springer Nature
- p. 240-252
FIT: Frequency-Based Image Translation for Domain Adaptive Object Detection