Large-to-small Image Resolution Asymmetry in Deep Metric Learning (Pavel Šuma)

Abstract:
Deep metric learning for vision is performed by optimizing a representation network to map (non-)matching image pairs to (non-)similar representations. During testing, which typically corresponds to image retrieval, both database and query examples are processed by the same network to obtain the representation used for similarity estimation and ranking. In this talk, we explore an asymmetric setup by light-weight processing of the query at a small image resolution to enable fast representation extraction. The goal is to obtain a network for database examples that is trained to operate on large resolution images and benefits from fine-grained image details, and a second network for query examples that operates on small resolution images but preserves a representation space aligned with that of the database network. We achieve this with a distillation approach that transfers knowledge from a fixed teacher network to a student via a loss that operates per image and solely relies on coupled augmentations without the use of any labels. In contrast to prior work that explores such asymmetry from the point of view of different network architectures, this work uses the same architecture but modifies the image resolution. We compare the performance/efficiency trade-off of resolution asymmetry and architecture asymmetry on three standard deep metric learning benchmarks, namely CUB200, Cars196, and SOP.

Speaker: Pavel Šuma (Ph.D. student, Visual Recognition Group, FEE CTU in Prague)

Key paper: Pavel Šuma and Giorgos Tolias. "Large-to-small Image Resolution Asymmetry in Deep Metric Learning." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023.