Guangyi Chen

Dr. Guangyi Chen

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
QCQiaosong Chu
Qiaosong Chu
SLShuyan Li
Shuyan Li
GCGuangyi Chen
Guangyi Chen
KLKai Li
Kai Li
XLXiu Li
Xiu Li
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most existing SFOD methods generate pseudo labels via a source-pretrained model to guide training, these pseudo labels usually contain high noises due to heavy domain discrepancy. In order to obtain better pseudo supervisions, we divide the target domain into source-similar and source-dissimilar parts and align them in the feature space by adversarial learning.Specifically, we design a detection variance-based criterion to divide the target domain. This criterion is motivated by a finding that larger detection variances denote higher recall and larger similarity to the source domain. Then we incorporate an adversarial module into a mean teacher framework to drive the feature spaces of these two subsets indistinguishable. Extensive experiments on multiple cross-domain object detection datasets demonstrate that our proposed method consistently outperforms the compared SFOD methods. Our implementation is available at https://github.com/ChuQiaosong.

1 January 2024
Verified
Conference Paper
Open access
PDF file
HYHanqi Yan
Hanqi Yan
YXYanzheng Xiang
Yanzheng Xiang
GCGuangyi Chen
Guangyi Chen
YWYifei Wang
Yifei Wang
LGLin Gui
Lin Gui
YHYulan He
Yulan He
Hanqi Yan, Yanzheng Xiang, Guangyi Chen, Yifei Wang, Lin Gui, Yulan He. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

26 October 2021 in arXiv
Verified
Preprint
Open access
PDF file
YRYongming Rao
Yongming Rao
GCGuangyi Chen
Guangyi Chen
JLJiwen Lu
Jiwen Lu
JZJie Zhou
Jie Zhou
Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. Specifically, we analyze the effect of the learned visual attention on network prediction through counterfactual intervention and maximize the effect to encourage the network to learn more useful attention for fine-grained image recognition. Empirically, we evaluate our method on a wide range of fine-grained recognition tasks where attention plays a crucial role, including fine-grained image categorization, person re-identification, and vehicle re-identification. The consistent improvement on all benchmarks demonstrates the effectiveness of our method. Code is available at https://github.com/raoyongming/CAL

11 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
QCQiaosong Chu
Qiaosong Chu
SLShuyan Li
Shuyan Li
GCGuangyi Chen
Guangyi Chen
KLKai Li
Kai Li
XLXiu Li
Xiu Li
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most existing SFOD methods generate pseudo labels via a source-pretrained model to guide training, these pseudo labels usually contain high noises due to heavy domain discrepancy. In order to obtain better pseudo supervisions, we divide the target domain into source-similar and source-dissimilar parts and align them in the feature space by adversarial learning. Specifically, we design a detection variance-based criterion to divide the target domain. This criterion is motivated by a finding that larger detection variances denote higher recall and larger similarity to the source domain. Then we incorporate an adversarial module into a mean teacher framework to drive the feature spaces of these two subsets indistinguishable. Extensive experiments on multiple cross-domain object detection datasets demonstrate that our proposed method consistently outperforms the compared SFOD methods.

18 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
GCGuangyi Chen
Guangyi Chen
JLJunlong Li
Junlong Li
NZNuoxing Zhou
Nuoxing Zhou
LRLiangliang Ren
Liangliang Ren
JLJiwen Lu
Jiwen Lu
Trajectory prediction is confronted with the dilemma to capture the multi-modal nature of future dynamics with both diversity and accuracy. In this paper, we present a distribution discrimination (DisDis) method to predict personalized motion patterns by distinguishing the potential distributions. Motivated by that the motion pattern of each person is personalized due to his/her habit, our DisDis learns the latent distribution to represent different motion patterns and optimize it by the contrastive discrimination. This distribution discrimination encourages latent distributions to be more discriminative. Our method can be integrated with existing multi-modal stochastic predictive models as a plug-and-play module to learn the more discriminative latent distribution. To evaluate the latent distribution, we further propose a new metric, probability cumulative minimum distance (PCMD) curve, which cumulatively calculates the minimum distance on the sorted probabilities. Experimental results on the ETH and UCY datasets show the effectiveness of our method.

17 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
GCGuangyi Chen
Guangyi Chen
YDYunlong Deng
Yunlong Deng
PZPeiyuan Zhu
Peiyuan Zhu
YLYan Li
Yan Li
YSYifan Shen
Yifan Shen
KZKun Zhang
Kun Zhang
Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal variables and causal structure. Existing evaluations often rely on either simplistic synthetic datasets or downstream performance on real-world tasks, generally suffering a dilemma between realism and evaluative precision. In this paper, we introduce a new benchmark for CRL using high-fidelity simulated visual data that retains both realistic visual complexity and, more importantly, access to ground-truth causal generating processes. The dataset comprises around 200 thousand images and 3 million video frames across 24 sub-scenes in four domains: static image generation, dynamic physical simulations, robotic manipulations, and traffic situation analysis. These scenarios range from static to dynamic settings, simple to complex structures, and single to multi-agent interactions, offering a comprehensive testbed that hopefully bridges the gap between rigorous evaluation and real-world applicability. In addition, we provide flexible access to the underlying causal structures, allowing users to modify or configure them to align with the required assumptions in CRL, such as available domain labels, temporal dependencies, or intervention histories. Leveraging this benchmark, we evaluated representative CRL methods across diverse paradigms and offered empirical insights to assist practitioners and newcomers in choosing or extending appropriate CRL frameworks to properly address specific types of real problems that can benefit from the CRL perspective. Welcome to visit our: Project page:https://causal-verse.github.io/, Dataset:https://huggingface.co/CausalVerse.