Skip to yearly menu bar Skip to main content


Poster

HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss

Yurun Tian · Axel Barroso Laguna · Tony Ng · Vassileios Balntas · Krystian Mikolajczyk

Poster Session 1 #280

Keywords: [ Algorithms ] [ Regression ] [ Algorithms -> Classification; Algorithms -> Meta-Learning; Algorithms -> Multitask and Transfer Learning; Algorithms ] [ Similar ]


Abstract:

In this paper, we investigate how L2 normalisation affects the back-propagated descriptor gradients during training. Based on our observations, we propose HyNet, a new local descriptor that leads to state-of-the-art results in matching. HyNet introduces a hybrid similarity measure for triplet margin loss, a regularisation term constraining the descriptor norm, and a new network architecture that performs L2 normalisation of all intermediate feature maps and the output descriptors. HyNet surpasses previous methods by a significant margin on standard benchmarks that include patch matching, verification, and retrieval, as well as outperforming full end-to-end methods on 3D reconstruction tasks.

Chat is not available.