Ge Luo

Ge Luo

Auto-generated profile, based on publicly available information

Ge Luo

Fudan University, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 May 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MWMengzhu Wang
Mengzhu Wang
JLJunze Liu
Junze Liu
GLGe Luo
Ge Luo
SWShanshan Wang
Shanshan Wang
WWWei Wang
Wei Wang
FNFeiping Nie
Feiping Nie
The training process of a domain generalization (DG) model involves utilizing one or more interrelated source domains to attain optimal performance on an unseen target domain. Existing DG methods often use auxiliary networks or require high computational costs to improve the model’s generalization ability by incorporating a diverse set of source domains. In contrast, this work proposes a method called S mooth-Guided Implicit Data Augmentation (SGIDA) that operates in the feature space to capture the diversity of source domains. To amplify the model’s generalization capacity, a distance metric learning (DML) loss function is incorporated. Additionally, rather than depending on deep features, the suggested approach employs logits produced from cross entropy (CE) losses with infinite augmentations. A theoretical analysis shows that logits are effective in estimating distances defined on original features, and the proposed approach is thoroughly analyzed to provide a better understanding of why logits are beneficial for DG. Moreover, to increase the diversity of the source domain, a sampling-based method called smooth is introduced to obtain semantic directions from interclass relations. The effectiveness of the proposed approach is demonstrated through extensive experiments on widely used DG, object detection, and remote sensing datasets, where it achieves significant improvements over existing state-of-the-art methods across various backbone networks.

26 October 2023
Verified
Conference Paper
Open access
MZManman Zhang
Manman Zhang
GLGe Luo
Ge Luo
YMYuchen Ma
Yuchen Ma
SLSheng Li
Sheng Li
Zhenxing QianZhenxing Qian
Zhenxing Qian
XZXinpeng Zhang
Xinpeng Zhang

28 October 2024
Verified
Conference Paper
Open access
GLGe Luo
Ge Luo
YMYuchen Ma
Yuchen Ma
MZManman Zhang
Manman Zhang
JHJunqiang Huang
Junqiang Huang
SLSheng Li
Sheng Li
XZXinpeng Zhang
Xinpeng Zhang
Multimodal Dialogue agents are often required to respond to conversation history using both textual and visual content. Even though current dialogue studies predominantly strive to generate natural texts or images, they fall short in considering the relevance of multimodal responses within a dialogue context, consequently confining agents from making prudent choices based on multiple alternatives and their associated relevance scores for decision-making. In this paper, we present a bidirectional multimodal dialogue framework that skillfully combines the forward generation of multiple text and image response candidates with reverse selection guided by relevance scores evaluated on dialogue context, facilitating agents in selecting the most suitable multimodal responses. Specifically, the forward generation aspect of our framework leverages a stage-wise approach, first producing textual replies and composite visual descriptions from the dialogue context, followed by the generation of visual responses aligned with the descriptions. In the reverse selection process, visual responses are translated into tangible descriptive texts that, in conjunction with textual responses, are inversely tied back to the dialogue context for relevance assessment, assigning a reference score to each multimodal response candidate to assist the intelligent agent in making informed decisions. Experimental outcomes demonstrate that our proposed bidirectional dialogue response framework markedly elevates performance in both automatic and human evaluations, yielding a range of contextually fitting multimodal responses for selection.

21 October 2023
Verified
Conference Paper
Open access
GLGe Luo
Ge Luo
MZManman Zhang
Manman Zhang
YMYuchen Ma
Yuchen Ma
SLSheng Li
Sheng Li
Zhenxing QianZhenxing Qian
Zhenxing Qian
XZXinpeng Zhang
Xinpeng Zhang
Multimodal Dialogue agents are often required to respond to conversation history using both textual and visual content. Even though current dialogue studies predominantly strive to generate natural texts or images, they fall short in considering the relevance of multimodal responses within a dialogue context, consequently confining agents from making prudent choices based on multiple alternatives and their associated relevance scores for decision-making. In this paper, we present a bidirectional multimodal dialogue framework that skillfully combines the forward generation of multiple text and image response candidates with reverse selection guided by relevance scores evaluated on dialogue context, facilitating agents in selecting the most suitable multimodal responses. Specifically, the forward generation aspect of our framework leverages a stage-wise approach, first producing textual replies and composite visual descriptions from the dialogue context, followed by the generation of visual responses aligned with the descriptions. In the reverse selection process, visual responses are translated into tangible descriptive texts that, in conjunction with textual responses, are inversely tied back to the dialogue context for relevance assessment, assigning a reference score to each multimodal response candidate to assist the intelligent agent in making informed decisions. Experimental outcomes demonstrate that our proposed bidirectional dialogue response framework markedly elevates performance in both automatic and human evaluations, yielding a range of contextually fitting multimodal responses for selection.