Diminishing Returns in Self-Supervised Learning

Transformer-based architectures have become a dominant paradigm in vision and language, but their success is often attributed to large model capacity and massive training data. In this work, we examine how self-supervised pre-training, intermediate fine-tuning, and downstream fine-tuning interact in a low-capacity regime, using a 5M-parameter Vision Transformer for semantic segmentation. Across multiple data scales, we find that masked image modeling pre-training and downstream fine-tuning reliably improve performance, but with clear diminishing returns as supervision increases. In contrast, inserting an intermediate classification fine-tuning stage consistently degrades downstream performance, with the largest drops occurring precisely where pre-training is most effective. Through an analysis of patch-level representation geometry, we show that classification-based intermediate supervision actively interferes with representations learned during pre-training by collapsing spatial structure critical for dense prediction. These results indicate that, in small models, the geometry of supervision matters more than the number of training stages: misaligned intermediate objectives can negate the benefits of pre-training rather than amplify them.