Young children develop sophisticated internal models of the world based on their visual experience. Can such models be learned from a child's visual experience without strong inductive biases? To investigate this, 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 and comprehensively evaluate their performance in downstream tasks using various reference models as yardsticks. On average, the best embedding models perform at a respectable 70% of a high-performance ImageNet-trained model, despite substantial differences in training data. They also learn broad semantic categories and object localization capabilities without explicit supervision, but they are less object-centric than models trained on all of ImageNet. Generative models trained with the same data successfully extrapolate simple properties of partially masked objects, like their rough outline, texture, color, or orientation, but struggle with finer object details. We replicate our experiments with two other children and find remarkably consistent 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：幼童基于自身视觉体验发展出精密的内心世界模型。此类模型能否在无须强归纳偏置的前提下，从儿童的视觉经验中习得？为探究此问题，我们采用单个儿童两年间收集的200小时头戴摄像头视频作为其视觉经验的现实代理，在无显式监督或领域特定归纳偏置的条件下，训练了最先进的神经网络。具体而言，我们同时训练了嵌入模型与生成模型，并以多种参考模型为基准，全面评估其在下游任务中的表现。平均而言，最佳嵌入模型的性能可达基于ImageNet训练的高性能模型的70%，尽管训练数据存在显著差异。这些模型无需显式监督即可习得广义语义类别与目标定位能力，但其目标中心性弱于基于完整ImageNet训练的模型。以相同数据训练的生成模型能成功外推出部分遮挡物体的简单属性（如大致轮廓、纹理、色彩或朝向），但在精细物体细节上表现不佳。我们使用另外两名儿童的数据重复实验，发现结果具有显著一致性。由此可见，具有广泛实用价值的高层视觉表征，可在无须强归纳偏置的前提下，从儿童视觉经验的代表性样本中稳健习得。