StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition

by   Yanqing Shen, et al.

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.


page 1

page 3

page 4

page 7

page 12

page 15


Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation

Existing knowledge distillation works for semantic segmentation mainly f...

Simplified TinyBERT: Knowledge Distillation for Document Retrieval

Despite the effectiveness of utilizing BERT for document ranking, the co...

Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection

Facial forgery detection is a crucial but extremely challenging topic, w...

Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition

The great success of deep learning is mainly due to the large-scale netw...

Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation

In this paper, we tackle the problem of novel visual category discovery,...

Tightly Coupled Learning Strategy for Weakly Supervised Hierarchical Place Recognition

Visual place recognition (VPR) is a key issue for robotics and autonomou...

Please sign up or login with your details

Forgot password? Click here to reset