Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations relied upon by such methods, however, are abstract. We aim to deconstruct this abstraction by expressing them as interpretable graphs over image views. We begin by theoretically showing that abstract relational representations are nothing but a way of recovering transitive relationships among local views. Based on this, we design Transitivity Recovering Decompositions (TRD), a graph-space search algorithm that identifies interpretable equivalents of abstract emergent relationships at both instance and class levels, and with no post-hoc computations. We additionally show that TRD is provably robust to noisy views, with empirical evidence also supporting this finding. The latter allows TRD to perform at par or even better than the state-of-the-art, while being fully interpretable. Implementation is available at https://github.com/abhrac/trd.

翻译：近期细粒度表征学习的进展借助局部到全局（涌现性）关系取得了最先进的结果。然而，此类方法所依赖的关系表征是抽象的。我们旨在通过将这些抽象关系表达为图像视图上的可解释图结构来解构其抽象性。首先从理论上证明，抽象关系表征本质上是一种恢复局部视图间传递性关系的方式。基于此，我们设计了传递性恢复分解（TRD），一种图空间搜索算法，能在实例和类别层面识别抽象涌现关系的可解释等价物，且无需事后计算。我们还证明了TRD对噪声视图具有可证明的鲁棒性，实验证据也支持这一发现。这使得TRD在完全可解释的同时，能够达到甚至超越最先进方法的性能。实现代码见https://github.com/abhrac/trd。