Young children develop sophisticated internal models of the world based on their egocentric visual experience. How much of this is driven by innate constraints and how much is driven by their experience? To investigate these questions, we train state-of-the-art neural networks on a realistic proxy of a child's visual experience without any explicit supervision or domain-specific inductive biases. Specifically, we train both embedding models and generative models on 200 hours of headcam video from a single child collected over two years. We train a total of 72 different models, exploring a range of model architectures and self-supervised learning algorithms, and comprehensively evaluate their performance in downstream tasks. The best embedding models perform at 70% of a highly performant ImageNet-trained model on average. They also learn broad semantic categories without any labeled examples and learn to localize semantic categories in an image without any location supervision. However, these models are less object-centric and more background-sensitive than comparable ImageNet-trained models. Generative models trained with the same data successfully extrapolate simple properties of partially masked objects, such as their texture, color, orientation, and rough outline, but struggle with finer object details. We replicate our experiments with two other children and find very similar results. Broadly useful high-level visual representations are thus robustly learnable from a representative sample of a child's visual experience without strong inductive biases.

翻译：幼儿基于自我中心的视觉经验发展出复杂的内部世界模型。这其中有多少源于先天约束，又有多少来自后天经验？为探究这些问题，我们在无显式监督或领域特定归纳偏置的条件下，基于儿童真实视觉经验代理数据训练了最先进的神经网络。具体而言，我们使用一名儿童两年间采集的200小时头部摄像头视频，分别训练了嵌入模型和生成模型。共训练72种不同模型，探索多种架构与自监督学习算法，并全面评估其下游任务表现。最佳嵌入模型平均性能达到高性能ImageNet训练模型的70%。这些模型无需标注样例即可学习广泛的语义类别，并在无位置监督条件下实现图像中语义类别的定位。然而，与同类ImageNet训练模型相比，它们更缺乏物体中心性且对背景更敏感。基于相同数据训练的生成模型能成功外推部分遮挡物体的简单属性（如纹理、颜色、朝向与大致轮廓），但在精细物体细节上表现不足。我们采用另外两名儿童的数据重复实验，结果高度一致。因此，无需强归纳偏置，从儿童视觉经验的代表性样本中便可稳健习得具有广泛实用性的高层视觉表征。