Xu Luo
I am currently a Ph.D student at University of Electronic Science and Technology of China (UESTC).
I am interested in understanding how visual representations behave in face of out-of-distribution tasks with limited labeled data, and in developing new algorithms that enable rapid model adaptation. This interesting direction connects several fields including visual representation learning, few-shot learning, meta-learning, model robustness and transfer learning.
Email  / 
CV  / 
Google Scholar  / 
Github
|
|
News
[2023/07] One paper was accepted to ICCV'23.
[2023/04] One paper was accepted to ICML'23.
[2022/09] One paper was accepted to NeurIPS'22.
[2022/05] One paper was accepted to ICML'22.
[2021/09] One paper was accepted to NeurIPS'21.
|
|
Less is More: On the Feature Redundancy of Pretrained Models When Transferring to Few-shot Tasks
Xu Luo,
Difan Zou,
Lianli Gao,
Zenglin Xu,
Jingkuan Song
arXiv, 2023
[PDF]
Uncovering and analyzing extreme feature redundancy phenomenon of pretrained vision models when transferring to few-shot tasks.
|
|
DETA: Denoised Task Adaptation for Few-shot Learning
Ji Zhang,
Lianli Gao,
Xu Luo,
Hengtao Shen,
Jingkuan Song
ICCV, 2023
[PDF]
[Code]
Proposing DETA--a framework that solves potential data/label noise in downstream few-shot transfer tasks.
|
|
A Closer Look at Few-shot Classification Again
Xu Luo*,
Hao Wu*,
Ji Zhang,
Lianli Gao,
Jing Xu,
Jingkuan Song
ICML, 2023
[PDF]
[Code]
Empirically proving the disentanglement of training and adaptation algorithms in few-shot classification, and performing interesting analysis of each phase that leads to the discovery of several important observations.
|
|
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
Jing Xu,
Xu Luo,
Xinglin Pan,
Yanan Li,
Wenjie Pei,
Zenglin Xu
NeurIPS, 2022   (Spotlight)
[PDF]
[Code]
Revealing a strong bias caused by the centroid of features in each few-shot learning task. A simple method is designed to rectify this bias by removing the dimension along the direction of task centroid from the feature space.
|
|
Channel Importance Matters in Few-Shot Image Classification
Xu Luo,
Jing Xu,
Zenglin Xu
ICML, 2022
[PDF]
[Code]
Revealing and analyzing the channel bias problem that we found critical in few-shot learning, through a simple channel-wise feature transformation applied only at test time.
|
|
Rectifying the Shortcut Learning of Background for Few-Shot Learning
Xu Luo,
Longhui Wei,
Liangjian Wen,
Jinrong Yang,
Lingxi xie,
Zenglin Xu,
Qi Tian
NeurIPS, 2021
[PDF]
[Code]
Identifying image background
as a shortcut knowledge ungeneralizable
beyond training categories in Few-Shot Learning. A novel framework, COSOC, is designed to
tackle this problem.
|
|
Boosting Few-Shot Classification with View-Learnable Contrastive Learning
Xu Luo,
Yuxuan Chen,
Liangjian Wen,
Lili Pan,
Zenglin Xu
ICME, 2021
[PDF]
[Code]
Applying contrastive learning to Few-Shot Learning, with views generated in a learning-to-learn fashion.
|
Academic service
Conference reviewer
NeurIPS 2023
ICML 2022, 2024
ICLR 2024
CVPR 2023, 2024
ICCV 2023
ECCV 2022, 2024
CoLLAs 2023, 2024
AAAI 2023
Journal reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Image Processing (TIP)
|
This well-designed template is borrowed from this guy
|
|