Wenjun Zeng

Uncertainty-Aware Few-Shot Image Classification

2020 · arXiv (Cornell University)

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set …

Self-Supervised Visual Representations Learning by Contrastive Mask Prediction

2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained datasets. …

WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

2021 · arXiv (Cornell University)

Domain generalization for semantic segmentation is highly demanded in real applications, where a trained model is expected to work well in previously unseen domains. One challenge lies in the lack of data which could cover …

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning

2023 · arXiv (Cornell University)

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the overestimation bias …