arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16965cs.CV
收藏

合成正样本的对比学习

Contrastive Learning with Synthetic Positives

University of Notre Dame(内布拉斯加大学达灵顿分校);Guangdong Provincial People’s Hospital(广东省级人民医院)

Dewen Zeng, Yawen Wu, Xinrong Hu, Xiaowei Xu, Yiyu Shi

AI总结:

提出CLSP方法,利用扩散模型生成合成正样本,提升对比学习性能,在多个基准上超越现有方法。

摘要:

利用最近邻的对比学习已被证明是最有效的自监督学习(SSL)技术之一,它利用了同一类别中多个实例的相似性。然而,其有效性受到限制,因为最近邻算法主要识别“容易”的正样本对,其中表示在嵌入空间中已经紧密相邻。在本文中,我们介绍了一种名为“合成正样本对比学习”(CLSP)的新方法,该方法利用由无条件扩散模型生成的合成图像作为额外的正样本,帮助模型从多样化的正样本中学习。通过在扩散模型采样过程中进行特征插值,我们生成具有不同背景但语义内容与锚定图像相似的图像。这些图像被视为锚定图像的“困难”正样本,当它们作为补充正样本纳入对比损失时,在多个基准数据集(如CIFAR10)上,与之前的NNCLR和All4One方法相比,线性评估的性能提升了超过2%和1%,达到了最先进的方法水平。在迁移学习基准上,CLSP在8个下游数据集中的6个上优于现有的SSL框架。我们相信CLSP为未来在训练过程中纳入合成数据的SSL研究建立了有价值的基线。

英文摘要:

Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is constrained as the nearest neighbor algorithm primarily identifies "easy" positive pairs, where the representations are already closely located in the embedding space. In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional positives to help the model learn from diverse positives. Through feature interpolation in the diffusion model sampling process, we generate images with distinct backgrounds yet similar semantic content to the anchor image. These images are considered "hard" positives for the anchor image, and when included as supplementary positives in the contrastive loss, they contribute to a performance improvement of over 2% and 1% in linear evaluation compared to the previous NNCLR and All4One methods across multiple benchmark datasets such as CIFAR10, achieving state-of-the-art methods. On transfer learning benchmarks, CLSP outperforms existing SSL frameworks on 6 out of 8 downstream datasets. We believe CLSP establishes a valuable baseline for future SSL studies incorporating synthetic data in the training process.

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。

↑