← Search

Fangtong Sun

2 accepted papers

2025

FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network

NeurIPS 2025poster

Low-light vision remains a fundamental challenge in computer vision due to severe illumination degradation, which significantly affects the performance of downstream tasks such as detection and segmentation. While recent state-of-the-art methods have improved performance through invariant feature le…

Cited by 0SourcecodeScholar
2025

MMTP: Meta-learning-based Multi-Textual Prompt Tuning for Visual-Language Models

ICASSP 2025accepted

Pre-trained Visual-Language Models (VLMs) have demonstrated powerful performance on various downstream tasks. Recently, many prompt tuning methods represented by Context Optimization (CoOp) have effectively adapted VLMs to few-shot tasks. However, the CoOp-based methods suffer from overfitting to ba…

Cited by 5SourceScholar