activity
20202023
most citedWeakly Supervised Disentangled Generative Causal Representation Learning

24 citations · 29 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2023

MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learning

Helbert Paat, Qing Lian, Weilong Yao +1

Advancements in deep learning-based 3D object detection necessitate the availability of large-scale datasets. However, this requirement introduces the challenge of manual annotatio…

cs.LG2022★ 1 cited

Minimax Regret Optimization for Robust Machine Learning under Distribution Shift

Alekh Agarwal, Tong Zhang

In this paper, we consider learning scenarios where the learned model is evaluated under an unknown test distribution which potentially differs from the training distribution (i.e.…

cs.LG2022★ 3 cited

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets

Han Zhong, Wei Xiong, Jiyuan Tan +4

We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset colle…

cs.CV2021★ 1 cited

Exploring Geometric Consistency for Monocular 3D Object Detection

Qing Lian, Botao Ye, Ruijia Xu +2

This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reve…

cs.LG2020★ 24 cited

Weakly Supervised Disentangled Generative Causal Representation Learning

Xinwei Shen, Furui Liu, Hanze Dong +3

This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information. Unlike existing disentanglement methods that en…