Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
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 finetuning in this paradigm, while little attention is paid to exploiting the annotation budget for finetuning. To fill in this gap, we formally define this new active finetuning task focusing on the selection of samples for annotation in the pretraining-finetuning paradigm. We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool and maintaining enough diversity by optimizing a parametric model in the continuous space. We prove that the Earth Mover's distance between the distributions of the selected subset and the entire data pool is also reduced in this process. Extensive experiments show the leading performance and high efficiency of ActiveFT superior to baselines on both image classification and semantic segmentation. Our code is released at https://github.com/yichen928/ActiveFT.
Code (1)
Tasks
Diversityimage-classificationImage ClassificationSemantic SegmentationSimilar Papers 제목 키워드 기반
ActiveDC: Distribution Calibration for Active Finetuning
The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requi…
image-classificationImage ClassificationBoundary Matters: A Bi-Level Active Finetuning Framework
The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetun…
Active LearningDenoisingDiversityThe Finetuner's Fallacy: When to Pretrain with Your Finetuning Data
Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting ge…
General KnowledgeDomain AdaptationImprove Unsupervised Pretraining for Few-label Transfer
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream …
ClusteringContrastive LearningDeep Active Learning: A Reality Check
We conduct a comprehensive evaluation of state-of-the-art deep active learning methods. Surprisingly, under general settings, no single-model method decisively outperforms entropy-based active learning, and some even fal…
Active Learningobject-detectionObject Detection