Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
This addresses the need for interpretability in fine-grained relationship analysis for computer vision researchers, though it is incremental as it builds on existing local-to-global methods.
The paper tackles the problem of abstract relational representations in fine-grained representation learning by deconstructing them into interpretable graphs over image views, showing that TRD achieves performance on par with or better than state-of-the-art methods while being fully interpretable.
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.