2 papers
cs.CV2024
Active Learning for Vision-Language Models
Bardia Safaei, Vishal M. Patel
Pre-trained vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot performance on a wide range of downstream computer vision tasks. However, there still exi…
cs.CV2024
Gradient-Regularized Out-of-Distribution Detection
Sina Sharifi, Taha Entesari, Bardia Safaei +2
One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addr…