Paper ID | MLSP-2.2 | ||
Paper Title | CANET: CONTEXT-AWARE LOSS FOR DESCRIPTOR LEARNING | ||
Authors | Tianyou Chen, Xiaoguang Hu, Jin Xiao, Guofeng Zhang, Hui Ruan, Beihang University, China | ||
Session | MLSP-2: Deep Learning Training Methods 2 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Research on designing local feature descriptors has gradually shifted to deep learning. Different from other computer vision tasks, the biggest challenge for local descriptor learning lies with the formulation of loss functions. Existing methods solve the problem by leveraging Siamese loss or triplet loss and improve the performance of the learned descriptors by a significant margin. However, the widely used Siamese loss and triplet loss cannot fully utilize the context information. In this paper, we propose a novel loss function to introduce more context information to facilitate training. After incorporating the proposed loss function into training, our learned descriptor demonstrates state-of-the-art performance in patch verification, image matching and patch retrieval benchmarks. The pretrained model will be publicly available at https://github.com/clelouch/CANet. |