← Search

Jianqi Zhang

2 accepted papers

2025

Less Yet Robust: Crucial Region Selection for Scene Recognition

ICASSP 2025accepted

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene…

Cited by 0SourceScholar
2024

Hacking Task Confounder in Meta-Learning

IJCAI 2024poster

Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization performance. However, our experiments reveal an unexpected result: ther…