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

Uncovering and analyzing extreme feature redundancy phenomenon of pretrained vision models when transferring to few-shot tasks.

Proposing DETA--a framework that solves potential data/label noise in downstream few-shot transfer tasks.

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.

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.

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.

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.

Applying contrastive learning to Few-Shot Learning, with views generated in a learning-to-learn fashion.

Conference reviewer

This well-designed template is borrowed from this guy