关注
Mohammad Mahdi Derakhshani
Mohammad Mahdi Derakhshani
University of Amsterdam, Video & Image Sense Lab
在 uva.nl 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Bayesian Prompt Learning for Image-Language Model Generalization
MM Derakhshani, E Sanchez, A Bulat, VGT da Costa, CGM Snoek, ...
ICCV, https://github.com/saic-fi/Bayesian-Prom, 2023
43*2023
Kernel Continual Learning
MM Derakhshani, X Zhen, L Shao, C Snoek
ICML, 2021
372021
Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors
MM Derakhshani, S Masoudnia, AH Shaker, O Mersa, MA Sadeghi, ...
CVPR, 2019
362019
Open-ended medical visual question answering through prefix tuning of language models
T van Sonsbeek, MM Derakhshani, I Najdenkoska, CGM Snoek, ...
MICCAI (Oral), 2023
322023
LifeLonger: A Benchmark for Continual Disease Classification
MM Derakhshani, I Najdenkoska, T van Sonsbeek, X Zhen, D Mahapatra, ...
MICCAI, 2022
292022
BlockCNN: A Deep Network for Artifact Removal and Image Compression
D Maleki, S Nadalian, MM Derakhshani, MA Sadeghi
CVPR workshop, 2018
262018
Any-Shift Prompting for Generalization over Distributions
Z Xiao, J Shen, MM Derakhshani, S Liao, CGM Snoek
CVPR, 2024
12024
Unlocking spatial comprehension in text-to-image diffusion models
MM Derakhshani, M Xia, H Behl, CGM Snoek, V Rühle
arXiv preprint arXiv:2311.17937, 2023
12023
Self-Supervised Open-Ended Classification with Small Visual Language Models
MM Derakhshani, I Najdenkoska, CGM Snoek, M Worring, YM Asano
ICLR ME-FoMo Workshop, 2023
1*2023
Variational prompt tuning improves generalization of vision-language foundation models
MM Derakhshani, E Sanchez, A Bulat, VGT da Costa, CGM Snoek, ...
ICLR ME-FoMo Workshop, 2023
2023
Method and system for kernel continuing learning
M Derakhshani, X Zhen, L Shao, C Snoek
US Patent App. 17/346,267, 2022
2022
Generative Kernel Continual learning
M Mahdi Derakhshani, X Zhen, L Shao, CGM Snoek
arXiv e-prints, arXiv: 2112.13410, 2021
2021
系统目前无法执行此操作,请稍后再试。
文章 1–12