paper-with-me

홈 › Papers

Efficient and Versatile Robust Fine-Tuning of Zero-shot Models

2024-08-11 · Sungyeon Kim, Boseung Jeong, Donghyun Kim, Suha Kwak

Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and demands extensive computational resources. We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks while simultaneously addressing both these issues. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Furthermore, we propose MPM-NCE loss designed for fine-tuning on vision-language downstream tasks. It ensures precise alignment of multiple image-text pairs and discriminative feature learning. By extending the benchmark for robust fine-tuning beyond classification to include diverse tasks such as cross-modal retrieval and open vocabulary segmentation, we demonstrate the broad applicability of R-Adapter. Our extensive experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.

📄 PDF Abstract BibTeX arXiv:2408.05749

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Modal Retrievalzero-shot-classificationZero-Shot Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Adapter 설명 없음

Similar Papers 제목 키워드 기반

InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT

2023-05-22 · Yichong Xu, Ruochen Xu, Dan Iter, Yang Liu 외

While large models such as GPT-3 demonstrate exceptional performance in zeroshot and fewshot summarization tasks, their extensive serving and fine-tuning costs hinder their utilization in various applications. Conversely…

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation

2023-03-15 · Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan 외

Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization. We propose UPRISE (Universal Promp…

HallucinationPrompt EngineeringRetrieval

Prompt-Learning for Fine-Grained Entity Typing

2021-11-16 · ACL ARR November 2021 11 · Anonymous

As an effective approach to tune pre-trained language models (PLMs) for specific tasks, prompt-learning has recently attracted much attention from researchers. By using cloze-style language prompts to stimulate the versa…

Entity TypingKnowledge ProbingLanguage ModelingLanguage Modelling+5

Prompt-Learning for Fine-Grained Entity Typing

2021-08-24 · Ning Ding, Yulin Chen, Xu Han, Guangwei Xu 외

As an effective approach to tune pre-trained language models (PLMs) for specific tasks, prompt-learning has recently attracted much attention from researchers. By using \textit{cloze}-style language prompts to stimulate …

Entity TypingKnowledge ProbingLanguage ModelingLanguage Modelling+5

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

2023-06-02 · NeurIPS 2023 11 · Cristina Menghini, Andrew Delworth, Stephen H. Bach

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudol…

image-classificationImage ClassificationZero-Shot Learning