paper-with-me

Papers

Boundary Matters: A Bi-Level Active Finetuning Framework

2024-03-15 · Han Lu, Yichen Xie, Xiaokang Yang, Junchi Yan

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 finetuning has emerged, aiming to select the most appropriate samples for model finetuning within a limited budget. Traditional active learning methods often struggle in this setting due to their inherent bias in batch selection. Furthermore, the recent active finetuning approach has primarily concentrated on aligning the distribution of selected subsets with the overall data pool, focusing solely on diversity. In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty. The process begins with the identification of pseudo-class centers, followed by an innovative denoising method and an iterative strategy for boundary sample selection in the high-dimensional feature space, all without relying on ground-truth labels. Our comprehensive experiments provide both qualitative and quantitative evidence of our method's efficacy, outperforming all the existing baselines.

📄 PDF Abstract BibTeX arXiv:2403.10069

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningDenoisingDiversity

Similar Papers 제목 키워드 기반

Interaction Matters: An Evaluation Framework for Interactive Dialogue Assessment on English Second Language Conversations

2024-07-09 · Rena Gao, Carsten Roever, Jey Han Lau

We present an evaluation framework for interactive dialogue assessment in the context of English as a Second Language (ESL) speakers. Our framework collects dialogue-level interactivity labels (e.g., topic management; 4 …

Management

Interactive Boundary Prediction for Object Selection

2018-09-01 · ECCV 2018 9 · Hoang Le, Long Mai, Brian Price, Scott Cohen 외

Interactive image segmentation is critical for many image editing tasks. While recent advanced methods on interactive segmentation focus on the region-based paradigm, more traditional boundary-based methods such as Intel…

DecoderImage SegmentationInteractive SegmentationObject+3

When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?

2021-11-01 · NeurIPS 2021 12 · Lijie Fan, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang 외

Contrastive learning (CL) can learn generalizable feature representations and achieve the state-of-the-art performance of downstream tasks by finetuning a linear classifier on top of it. However, as adversarial robustnes…

Adversarial RobustnessContrastive Learningimage-classificationImage Classification+1

FACT: A Simple and Efficient Framework for Active Finetuning

2026-06-01 · Wenshuai Xu, You Song, Yuzhuo Cui, Minjie Ren 외 arxiv

The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging data. Previous research has predominantly…

Image ClassificationActive Learning

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