Discriminative Features Matter: Multi-layer Bilinear Pooling for Camera Localization

Xin Wang, Xiang Wang, Chen Wang, Xiao Bai, Jing Wu, Edwin R Hancock

Research output: Contribution to conferencePaperpeer-review


Deep learning based camera localization from a single image has been explored recently since these methods are computationally efficient. However, existing methods only provide general global representations, from which an accurate pose estimation can not be reliably derived. We claim that effective feature representations for accurate pose estimation shall be both "informative" (focusing on geometrically meaningful regions) and "discriminative" (accounting for different poses of similar images). Therefore, we propose a novel multi-layer factorized bilinear pooling module for feature aggregation. Specifically, informative features are selected via bilinear pooling, and discriminative features are highlighted via multi-layer fusion. We develop a new network for camera localization using the proposed feature pooling module. The effectiveness of our approach is demonstrated by experiments on an outdoor Cambridge Landmarks dataset and an indoor 7 Scenes dataset. The results show that focusing on discriminative features significantly improves the network performance of camera localization in most cases. Codes will be available soon.
Original languageEnglish
Number of pages12
Publication statusAccepted/In press - 23 Jul 2019
EventBritish Machine Vision Conference - Cardiff, Cardiff, United Kingdom
Duration: 9 Sep 201912 Sep 2019


ConferenceBritish Machine Vision Conference
Abbreviated titleBMVC 2019
Country/TerritoryUnited Kingdom
Internet address

Bibliographical note

© 2019. The copyright of this document resides with its authors

Cite this