I am a PhD student in the IMAGINE team, École des Ponts ParisTech, advised by Prof. Mathieu Aubry. I graduated from the Master Vision et Apprentissage (MVA, ENS Paris-Saclay) and Engineering Program at Ecole des Ponts ParisTech. Before that, I received dual B.S. degrees in Mechanics from Université Claude Bernard Lyon and Physics from Wuhan University.
I am interested in Computer Vision, Deep Learning. My research mainly focuses on finding solutions to image/video tasks without annotations (unsupervised learning) or with easy accessible annotations (weakly supervised learning).
2019.12 : Our paper " Empirical Bayes Transductive Meta-Learning with Synthetic Gradients" accepted at ICLR 2020
2019.08 : Our paper " Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach" is on arXiv. In this work, we propose a simple and effective method to solve a challenging fine-grained cross-domain recognition problem: ~16K classes but with only ~6K annotations.
2019.05 : Visiting scholar at BAIR, UC Berkeley
2019.03 : Our paper "Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning" accepted at CVPR 2019, was featured in several medias such as Nature, TechXplore, 机器之心 etc.
2019.01 : Our paper "Marginalized Average Attentional Network For Weakly-Supervised Learning" accepted at ICLR 2019