Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and successfully implement this in vision transformers. Our shape-optimized vision transformer, SoViT, achieves results competitive with models that exceed twice its size, despite being pre-trained with an equivalent amount of compute. For example, SoViT-400m/14 achieves 90.3% fine-tuning accuracy on ILSRCV2012, surpassing the much larger ViT-g/14 and approaching ViT-G/14 under identical settings, with also less than half the inference cost. We conduct a thorough evaluation across multiple tasks, such as image classification, captioning, VQA and zero-shot transfer, demonstrating the effectiveness of our model across a broad range of domains and identifying limitations. Overall, our findings challenge the prevailing approach of blindly scaling up vision models and pave a path for a more informed scaling.

翻译：规模法则近期被用于推导在给定计算时长下的计算最优模型规模（参数数量）。我们对此类方法进行了深化与改进，以推断计算最优的模型形态（如宽度与深度），并在视觉Transformer中成功实现。经形态优化的视觉Transformer——SoViT——虽以等量计算资源完成预训练，其性能却可媲美规模翻倍的模型。例如，SoViT-400m/14在ILSRCV2012上达到90.3%的微调准确率，超越规模更大的ViT-g/14，逼近相同设置下的ViT-G/14，且推理成本不足其半数。我们针对图像分类、图像描述、视觉问答及零样本迁移等多项任务展开全面评估，证明了模型在广泛领域的有效性，并揭示了其局限性。总体而言，本研究挑战了盲目扩大视觉模型规模的既有范式，为更科学的规模扩展开辟了新路径。