Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale dataset and human-annotated labels, recent large-scale datasets contain several problems in terms of privacy violations, inadequate fairness protection, and labor-intensive annotation. In the present paper, we pre-train ViT without any image collections and annotation labor. We experimentally verify that our proposed framework partially outperforms sophisticated Self-Supervised Learning (SSL) methods like SimCLRv2 and MoCov2 without using any natural images in the pre-training phase. Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent. For example, the performance rates on the CIFAR-10 dataset are as follows: our proposal 97.6 vs. SimCLRv2 97.4 vs. ImageNet 98.0.
翻译:我们能否在没有自然图像和附加说明的标签的情况下完成愿景变异器(VIT)的预培训?虽然经过预先培训的VIT似乎严重依赖大规模数据集和人文附加说明的标签,但最近的大型数据集在侵犯隐私、不适当的公平保护和劳动密集型注释方面包含若干问题。在本文件中,我们在没有任何图像收藏和批注劳动的情况下对VIT进行预培训。我们实验性地核实,我们提议的框架部分地超过了SimCLRv2和MOCov2等复杂的自我强化学习方法,而没有在培训前阶段使用任何自然图像。此外,虽然未经事先培训的VIT在没有自然图像的情况下生成了一些与图像网络事先培训的VIT不同的视觉化,但它可以在很大程度上解释自然图像数据集。例如,CIFAR-10数据集的性能率如下:我们的提案97.6对SimCLRv2 97.4 vs.imcLRev98.0。