Weijie Chen

Weijie Chen

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2022
Verified
Book Chapter
Closed access
PDF file
RMRang Meng
Rang Meng
XLXianfeng Li
Xianfeng Li
WCWeijie Chen
Weijie Chen
SYShicai Yang
Shicai Yang
JSJie Song
Jie Song
SPShiliang Pu
Shiliang Pu

25 October 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
QLQinghai Lang
Qinghai Lang
LZLei Zhang
Lei Zhang
WSWenxu Shi
Wenxu Shi
WCWeijie Chen
Weijie Chen
SPShiliang Pu
Shiliang Pu
Recent researches have made a great progress in domain adaptive object detectors. These detectors aim to learn explicit domain-invariant features by adversarially mitigating domain divergence and simultaneously optimizing source risks. However, an inherent problem is that they ignore the informative knowledge implied in domain-specific features, which is recognized as implicit domain-invariant feature. This is mainly caused by the multimode structure underlying target distribution, characterized by various scales and categories of objects in target images. To solve that, we propose the Implicit Domain-invariant Faster R-CNN (IDF) by using non-adversarial domain discriminator, dual attention mechanism and selective feature perception. This idea is implemented on the Faster R-CNN backbone, but with an improved architecture of two branches, i.e. domain-invariant branch and domain-specific branch. The former can clearly learn explicit domain adaptive features w.r.t. easy samples, while the latter aims to learn implicit domain-invariant features w.r.t. hard samples. Experiments on numerous benchmark datasets, including the Cityscapes, Foggy Cityscapes, KITTI and SIM10K, show the superiority of our IDF over other state-of-the-art domain adaptive object detectors. The demo code is released in https://github.com/sea123321/IDF.

20 January 2024 in Pattern Recognition
Verified
Journal Article
Closed access
LLLuojun Lin
Luojun Lin
HXHan Xie
Han Xie
ZSZhishu Sun
Zhishu Sun
WCWeijie Chen
Weijie Chen
WLWenxi Liu
Wenxi Liu
LZLei Zhang
Lei Zhang

24 August 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LZLei Zhang
Lei Zhang
LQLingyun Qin
Lingyun Qin
MXMingjun Xu
Mingjun Xu
WCWeijie Chen
Weijie Chen
SPShiliang Pu
Shiliang Pu
WZWensheng Zhang
Wensheng Zhang
We propose a Meta Learning on Randomized Transformations (MLRT) to learn domain invariant object detectors. Domain generalization is a problem about learning an invariant model from multiple source domains which can generalize well on unseen target domains. This problem is overlooked in object detection field, which is formally named as domain generalizable object detection (DGOD). Moreover, existing domain generalization methods have the problem of domain bias so that they can easily overfit to some specific domain (e.g., source domain). In order to alleviate the domain bias, in MLRT model, a novel randomized spectrum transformation (RST) module is proposed to increase the diversity of source domains. Specifically, RST randomizes the domain specific information of images in frequency-space, which can transform single or multiple source domains into various new domains. Besides, we observe a prior that the gradient imbalance degree among domains can also reflect the domain bias. Therefore, we further propose to alleviate the domain bias from the perspective of gradient balancing, and a novel gradient weighting (GW) module is proposed to balance the gradients over all domains via a hand-crafted weight. Finally we embed our RST and GW into a general meta learning framework and the proposed MLRT model is formalized for DGOD task. Extensive experiments are conducted on six benchmarks, and our method achieves the SOTA performance.

4 November 2023 in Knowledge-Based Systems
Verified
Journal Article
Closed access
WCWeijie Chen
Weijie Chen
YXYunyi Xuan
Yunyi Xuan
SYShicai Yang
Shicai Yang
DXDi Xie
Di Xie
LLLuojun Lin
Luojun Lin
YZYueting Zhuang
Yueting Zhuang

26 October 2023
Verified
Conference Paper
Open access
YXYunyi Xuan
Yunyi Xuan
WCWeijie Chen
Weijie Chen
SYShicai Yang
Shicai Yang
DXDi Xie
Di Xie
LLLuojun Lin
Luojun Lin
YZYueting Zhuang
Yueting Zhuang
Data-Free Knowledge Distillation (DFKD) has shown great potential in creating a compact student model while alleviating the dependency on real training data by synthesizing surrogate data. However, prior arts are seldom discussed under distribution shifts, which may be vulnerable in real-world applications. Recent Vision-Language Foundation Models, e.g., CLIP, have demonstrated remarkable performance in zero-shot out-of-distribution generalization, yet consuming heavy computation resources. In this paper, we discuss the extension of DFKD to Vision-Language Foundation Models without access to the billion-level image-text datasets. The objective is to customize a student model for distribution-agnostic downstream tasks with given category concepts, inheriting the out-of-distribution generalization capability from the pre-trained foundation models. In order to avoid generalization degradation, the primary challenge of this task lies in synthesizing diverse surrogate images driven by text prompts. Since not only category concepts but also style information are encoded in text prompts, we propose three novel Prompt Diversification methods to encourage image synthesis with diverse styles, namely Mix-Prompt, Random-Prompt, and Contrastive-Prompt. Experiments on out-of-distribution generalization datasets demonstrate the effectiveness of the proposed methods, with Contrastive-Prompt performing the best.