Learning More by Seeing Less: Structure-First Learning for Efficient, Transferable, and Human-Aligned Vision

Tianqin Li, George Liu, Tai Sing Lee

Keywords: Structure-first learning, Line drawings, Data efficiency, Generalization, Human-aligned vision, Shape bias, Sparse representations, Knowledge distillation

TL;DR: By training vision models on structure before color photographs, we create more efficient, robust, and human-aligned systems that prioritize structural understanding over superficial appearance.

Abstract: Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations like line drawings, suggesting that structure, rather than appearance, underlies efficient visual understanding. In this work, we propose a novel structure-first learning paradigm that uses line drawings as an initial training modality to induce more compact and generalizable visual representations. We demonstrate that models trained with this approach develop a stronger shape bias, more focused attention, and greater data efficiency across classification, detection, and segmentation tasks. Notably, these models also exhibit lower intrinsic dimensionality, requiring significantly fewer principal components to capture representational variance, which mirrors observations of low-dimensional, efficient representations in the human brain. Beyond performance improvements, structure-first learning produces more compressible representations, enabling better distillation into lightweight student models. Students distilled from teachers trained on line drawings consistently outperform those trained from color-supervised teachers, highlighting the benefits of structurally compact knowledge. Together, our results support the view that structure-first visual learning fosters efficiency, generalization, and human-aligned inductive biases, offering a simple yet powerful strategy for building more robust and adaptable vision systems.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 11475