Long (Tony) Lian


I am a researcher at UC Berkeley under the supervision of Prof. Stella Yu. I obtained my B.A. in Computer Science at UC Berkeley. I am primarily interested in data-efficient computer vision algorithms that leverage various forms of supervision. I was previously supervised by David Anthoff and contributed to the Queryverse project. I also had research experiences as an intern in Baidu’s distributed deep learning framework team.

Email / CV / Google Scholar / LinkedIn / Github

Publications (*: equal contribution)

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

Xudong Wang*, Long Lian*, Stella X. Yu

To appear in ECCV 2022

We focus on selecting the right data to query for label for semi-supervised learning without any label or task information. Our method demonstrates that a small compute spent on careful labeled data selection brings big annotation efficiency.

Debiased Learning from Naturally Imbalanced Pseudo-Labels

Xudong Wang, Zhirong Wu, Long Lian, Stella X. Yu

CVPR 2022

We propose a novel and effective debiased learning method based on counterfactual reasoning and adaptive margins to deal with the undesired effect from naturally imbalanced pseudo-labels.

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Xudong Wang*, Long Lian*, Stella X. Yu

CVPR 2021

Rather than training a universal RL policy invariant to train-test distribution shift, we proposed unsupervised visual attention and invariance method (VAI) to disperse interference task-irrelevant factors towards a RL policy robust to distractions.

Long-tailed Recognition by Routing Diverse Distribution-aware Experts

Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu, Stella X. Yu

ICLR 2021 (Spotlight)

Leveraging bias-variance tradeoff, we proposed a universal classification framework for long-tailed distributed data with RoutIng Diverse Experts (RIDE) that improves both accuracy and inference speed.

Academic Services

Reviewer for CVPR 2022/ECCV 2022

Side Projects

Rainbow: An implementation of Rainbow algorithm with PARL reinforcement learning framework.

AnimeGAN.js: An implementation of AnimeGAN with tf.js, which converts photos to anime style online.