SOLAR: Second-order Loss And Attention For Image Retrieval
2020 · Tony Ng, Vassileios Balntas, Yurun Tian, et al.
Abstract
Recent works in deep-learning have shown that second-order information is beneficial in many computer-vision tasks. Second-order information can be enforced both in the spatial context and the abstract feature dimensions. In this work, we explore two second-order components. One is focused on second-order spatial information to increase the performance of image descriptors, both local and global. It is used to re-weight feature maps, and thus emphasise salient image locations that are subsequently used for description. The second component is concerned with a second-order similarity (SOS) loss, that we extend to global descriptors for image retrieval, and is used to enhance the triplet loss with hard-negative mining. We validate our approach on two different tasks and datasets for image retrieval and image matching. The results show that our two second-order components complement each other, bringing significant performance improvements in both tasks and lead to state-of-the-art result
Authors
(none)
Tags
Stats
Related papers
- Sosnet: Second Order Similarity Regularization For Local Descriptor Learning (2019)18.70
- Learning Super-features For Image Retrieval (2022)4.31
- Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11
- DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
- Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
- DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95
- Local Feature Detectors, Descriptors, And Image Representations: A Survey (2016)0.00
- End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66