Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence

Octave Mariotti, Zhipeng Du, Yash Sanjay Bhalgat, Oisin Mac Aodha, Hakan Bilen

Keywords: Semantic Correspondence, Evaluation, Generalization, Representation Learning

TL;DR: We show that supervised semantic correspondence methods fail to generalize well to unseen keypoints and we introduce geometric constraints during training to address this.

Abstract: Semantic correspondence (SC) aims to establish semantically meaningful matches across different instances of an object category. We illustrate how recent supervised SC methods remain limited in their ability to generalize beyond sparsely annotated training keypoints, effectively acting as keypoint detectors. To address this, we propose a novel approach for learning dense correspondences by lifting 2D keypoints into a canonical 3D space using monocular depth estimation. Our method constructs a continuous canonical manifold that captures object geometry without requiring explicit 3D supervision or camera annotations. Additionally, we introduce SPair-U, an extension of SPair-71k with novel keypoint annotations, to better assess generalization. Experiments not only demonstrate that our model significantly outperforms supervised baselines on unseen keypoints, highlighting its effectiveness in learning robust correspondences, but that unsupervised baselines outperform supervised counterparts when generalized across different datasets.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 12216