Progress in AI has largely been driven by methods that assume less. As compute and data increase, approaches with weaker inductive biases generally outperform those with stronger assumptions. This is particularly characteristic of the field of Visual Representation Learning, where approaches have gone from being dominated by Supervised Learning, to Weakly Supervised Learning, to the now widespread success of Self-Supervised Learning without human labels. Yet, even modern Self-Supervised Learning approaches still depend on strong inductive biases such as augmentations, masking, or cropping. If this trend holds, even these remaining biases should become bottlenecks at scale -- and our experiments confirm this: the optimal strength of inductive biases decreases as data grows. This motivates the search for approaches that rely on fewer assumptions. To this end, we introduce Temporal Difference in Vision (TDV), a new paradigm for self-supervised learning from video that avoids existing inductive biases, relying instead on a causal assumption that the past causes the future. TDV functions by jointly training an image encoder and a motion encoder so that the current frame's representation plus the encoded motion equals the next frame's representation. Despite not leveraging any strong inductive biases, TDV matches state-of-the-art recipes on dense spatial tasks, laying the foundation for representation learning without strong assumptions.

翻译：人工智能的进步很大程度上由假设更少的方法推动。随着计算和数据量的增加，具有较弱归纳偏置的方法通常优于具有较强假设的方法。这在视觉表征学习领域尤为典型，该领域的方法从监督学习主导，到弱监督学习，再到如今无需人工标签的自监督学习的广泛成功。然而，即便是现代的自监督学习方法仍依赖于诸如数据增强、掩码或裁剪等强归纳偏置。如果这一趋势持续，这些剩余的偏置在大规模场景下将成为瓶颈——我们的实验也证实了这一点：随着数据增长，归纳偏置的最优强度会下降。这促使我们寻找依赖更少假设的方法。为此，我们提出了视觉时间差异（TDV），一种从视频中进行自监督学习的新范式，该范式避免了现有的归纳偏置，转而依赖于一个因果假设：过去导致未来。TDV通过联合训练图像编码器和运动编码器实现功能，使得当前帧的表征加上编码后的运动等于下一帧的表征。尽管没有利用任何强归纳偏置，TDV在密集空间任务上达到了最先进的水平，为无需强假设的表征学习奠定了基础。