1 citations · 1 across the 3 of their papers we have counts for
3 papers
cs.CV2024★ 1 cited
RobustSAM: Segment Anything Robustly on Degraded Images
Wei-Ting Chen, Yu-Jiet Vong, Sy-Yen Kuo +2
Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting sys…
cs.CL2023
Self-Detoxifying Language Models via Toxification Reversal
Chak Tou Leong, Yi Cheng, Jiashuo Wang +2
Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can b…
cs.LG2023
Exploring Adversarial Attacks on Neural Networks: An Explainable Approach
Justus Renkhoff, Wenkai Tan, Alvaro Velasquez +7
Deep Learning (DL) is being applied in various domains, especially in safety-critical applications such as autonomous driving. Consequently, it is of great significance to ensure t…