arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14548cs.CV
收藏

在朋友们的帮助下:视觉表征的最近邻对比学习

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

Google Research(谷歌研究院);DeepMind(深度思维公司)

Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

摘要:

基于实例判别的自监督学习算法训练编码器对相同实例的预定义变换保持不变。虽然大多数方法将同一图像的不同视图视为对比度损失的阳性,但我们对使用数据集中其他实例的阳性感兴趣。我们的方法,视觉表示的最近邻对比学习(NNNN),从潜在空间中的数据集采样最近邻,并将它们视为阳性。这提供了比预定义转换更多的语义变化。我们发现,在对比损失中使用最近邻作为阳性,可以显着提高ImageNet分类的性能,从71.7%提高到75.6%,优于以前的最先进方法。在半监督学习基准测试中,当只有1%的ImageNet标签可用时,我们将性能从53.8%提高到56.5%。在迁移学习基准测试中,我们的方法在12个下游数据集中的8个上优于最先进的方法(包括ImageNet的监督学习)。此外,我们的经验表明,我们的方法是不太依赖于复杂的数据增强。当我们仅使用随机作物进行训练时,我们看到ImageNet Top-1准确率相对降低了2.1%。

英文摘要:

Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a contrastive loss, we are interested in using positives from other instances in the dataset. Our method, Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR), samples the nearest neighbors from the dataset in the latent space, and treats them as positives. This provides more semantic variations than pre-defined transformations. We find that using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification, from 71.7% to 75.6%, outperforming previous state-of-the-art methods. On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.8% to 56.5%. On transfer learning benchmarks our method outperforms state-of-the-art methods (including supervised learning with ImageNet) on 8 out of 12 downstream datasets. Furthermore, we demonstrate empirically that our method is less reliant on complex data augmentations. We see a relative reduction of only 2.1% ImageNet Top-1 accuracy when we train using only random crops.

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。

↑