Robust fine-tuning of zero-shot models-Reference-Cited by-同舟云学术

Robust fine-tuning of zero-shot models

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Wortsman Mitchell¹,Ilharco Gabriel¹,Kim Jong Wook²,Li Mike³,Kornblith Simon⁴,Roelofs Rebecca⁴,Lopes Raphael Gontijo⁴,Hajishirzi Hannaneh¹,Farhadi Ali¹,Namkoong Hongseok³,Schmidt Ludwig¹

Affiliation:

1. University of Washington

2. OpenAI

3. Columbia University

4. Google Research, Brain Team

Funder

NSF

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09878622.pdf?arnumber=9878622

Reference111 articles.

1. Ensembles and cocktails: Robust finetuning for natural language generation;hewitt;NeurIPS 2021 Workshop on Distribution Shifts,2021

2. Natural Adversarial Examples

3. On calibration of modern neural networks;guo;International Conference on Machine Learning (ICML),2017

4. Qual-itatively characterizing neural network optimization problems;goodfellow;International Conference on Learning Representations (ICLR),2014

Cited by 101 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders;Pattern Recognition;2024-09

2. Fine-tuning protein language models boosts predictions across diverse tasks;Nature Communications;2024-08-28

3. Few-shot adaptation of multi-modal foundation models: a survey;Artificial Intelligence Review;2024-08-27

4. Masked Channel Modeling for Bootstrapping Visual Pre-training;International Journal of Computer Vision;2024-08-16

5. Vision-Language Models for Vision Tasks: A Survey;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-08