arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.01531cs.CV
收藏

MoBYv2AL:用于图像分类的自监督主动学习

MoBYv2AL: Self-supervised Active Learning for Image Classification

Imperial College London(伦敦帝国理工学院);University College London(伦敦大学学院);KAIST(韩国科学技术院)

Razvan Caramalau, Binod Bhattarai, Danail Stoyanov, Tae-Kyun Kim

摘要:

主动学习(AL)最近在深度学习(DL)模型中流行起来。这是由于高效和信息丰富的采样,特别是当学习者需要大规模标记数据集时。通常,采样和训练在添加更多批次时分阶段进行。该策略的一个主要瓶颈是模型学习到的影响整体AL选择的狭窄表示。我们提出了MoBYv2AL,一种新的自监督主动学习框架的图像分类。我们的贡献在于将最成功的自监督学习算法之一MoBY提升到AL管道。因此,我们增加了下游任务感知的目标函数,并与对比损失联合优化。此外,我们推导出一个数据分布的选择函数,从标记的新的例子。最后,我们测试和研究我们的管道的鲁棒性和性能的图像分类任务。与最近的AL方法相比,我们成功地实现了最先进的结果。可用代码:https://github.com/razvancaramalau/MoBYv2AL

英文摘要:

Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods. Code available: https://github.com/razvancaramalau/MoBYv2AL

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑