paper-with-me

홈 › Papers

Fine-tuning Vision Classifiers On A Budget

2024-09-30 · Sunil Kumar, Ted Sandler, Paulina Varshavskaya

Fine-tuning modern computer vision models requires accurately labeled data for which the ground truth may not exist, but a set of multiple labels can be obtained from labelers of variable accuracy. We tie the notion of label quality to confidence in labeler accuracy and show that, when prior estimates of labeler accuracy are available, using a simple naive-Bayes model to estimate the true labels allows us to label more data on a fixed budget without compromising label or fine-tuning quality. We present experiments on a dataset of industrial images that demonstrates that our method, called Ground Truth Extension (GTX), enables fine-tuning ML models using fewer human labels.

📄 PDF Abstract BibTeX arXiv:2410.00085

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

AutoML: Exploration v.s. Exploitation

2019-12-23 · Hassan Eldeeb, Abdelrhman Eldallal

Building a machine learning (ML) pipeline in an automated way is a crucial and complex task as it is constrained with the available time budget and resources. This encouraged the research community to introduce several s…

AutoMLMeta-Learning

Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning

2024-08-16 · Alessio Devoto, Federico Alvetreti, Jary Pomponi, Paolo Di Lorenzo 외

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy a…

parameter-efficient fine-tuning

Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm

2023-03-25 · CVPR 2023 1 · Yichen Xie, Han Lu, Junchi Yan, Xiaokang Yang 외

Given the large-scale data and the high annotation cost, pretraining-finetuning becomes a popular paradigm in multiple computer vision tasks. Previous research has covered both the unsupervised pretraining and supervised…

Diversityimage-classificationImage ClassificationSemantic Segmentation

ConvNets Match Vision Transformers at Scale

2023-10-25 · Samuel L. Smith, Andrew Brock, Leonard Berrada, Soham De

Many researchers believe that ConvNets perform well on small or moderately sized datasets, but are not competitive with Vision Transformers when given access to datasets on the web-scale. We challenge this belief by eval…

Optimal Budgeted Adaptation of Large Language Models

2026-02-01 · Jing Wang, Jie Shen, Dean Foster, Zohar Karnin 외 arxiv

The trade-off between labeled data availability and downstream accuracy remains a central challenge in fine-tuning large language models (LLMs). We propose a principled framework for \emph{budget-aware supervised fine-tu…