Xiaokang Yang

M-Mix

2022 · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Negative pairs, especially hard negatives as combined with common negatives (easy to discriminate), are essential in contrastive learning, which plays a role of avoiding degenerate solutions in the sense of constant representation across different instances. …

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 …

Reflection Invariance Learning for Few-shot Semantic Segmentation

2023 · arXiv (Cornell University)

Few-shot semantic segmentation (FSS) aims to segment objects of unseen classes in query images with only a few annotated support images. Existing FSS algorithms typically focus on mining category representations from the single-view support to …

Domain-Controlled Prompt Learning

2023 · arXiv (Cornell University)

Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote sensing images (RSIs), medical images, …