This paper asks whether current self-supervised learning methods, if sufficiently scaled up, would be able to reach human-level visual object recognition capabilities with the same type and amount of visual experience humans learn from. Previous work on this question only considered the scaling of data size. Here, we consider the simultaneous scaling of data size, model size, and image resolution. We perform a scaling experiment with vision transformers up to 633M parameters in size (ViT-H/14) trained with up to 5K hours of human-like video data (long, continuous, mostly egocentric videos) with image resolutions of up to 476x476 pixels. The efficiency of masked autoencoders (MAEs) as a self-supervised learning algorithm makes it possible to run this scaling experiment on an unassuming academic budget. We find that it is feasible to reach human-level object recognition capacity at sub-human scales of model size, data size, and image size, if these factors are scaled up simultaneously. To give a concrete example, we estimate that a 2.5B parameter ViT model trained with 20K hours (2.3 years) of human-like video data with a spatial resolution of 952x952 pixels should be able to reach roughly human-level accuracy on ImageNet. Human-level competence is thus achievable for a fundamental perceptual capability from human-like perceptual experience (human-like in both amount and type) with extremely generic learning algorithms and architectures and without any substantive inductive biases.

翻译：本文探讨了当前自监督学习方法在充分扩展后，是否能够以人类视觉学习的相同类型和数量的经验，达到人类级的视觉物体识别能力。此前关于该问题的研究仅考虑了数据规模的扩展，而本文则同时考虑数据规模、模型规模与图像分辨率的协同扩展。我们使用视觉变换器（Vision Transformers）进行了规模扩展实验，模型参数量高达6.33亿（ViT-H/14），训练数据为长达5000小时的类人视频数据（长时、连续、大多为自我中心视角的视频），图像分辨率最高达476×476像素。掩码自编码器（MAEs）作为自监督学习算法的高效性，使得这项规模扩展实验能够在普通学术预算下实现。研究发现：若同时扩展模型规模、数据规模和图像尺寸，即使其规模低于人类水平，达到人类级物体识别能力也是可行的。具体而言，我们估计一个25亿参数的ViT模型，使用2.3万小时（约2.3年）的类人视频数据（空间分辨率952×952像素）进行训练，便能在ImageNet上达到近乎人类级的精准度。因此，基于极简的通用学习算法与架构，不依赖任何实质性归纳偏置，仅通过类人感知经验（在数量与类型上均与人类相似）即可实现基础感知能力的人类级竞争力。