DIEONet: Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition
Source abstract
Abstract
Visual Place Recognition (VPR) technology aims to use visual information to judge the location of agents, which plays an irreplaceable role in tasks such as loop closure detection and relocation. It is well known that previou... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Robotics and Sensor-Based Localization · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (28)
Show source-provided references
1. Visual place recognition: a survey from deep learning perspective10.1016/j.patcog.2020.107760 ↗
2. A constant-time efficient stereo SLAM system
3. Experience-based navigation for long-term localisation10.1177/0278364913499193 ↗
4. NetVLAD: CNN architecture for weakly supervised place recognition10.1109/TPAMI.2017.2711011 ↗
5. Deep visual geo-localization benchmark
6. Oquab M, Darcet T, Moutakanni T, Vo H, Szafraniec M, Khalidov V, et al. DINOv2: learning robust visual features without supervision. arXiv:2304.07193. 2023.
7. Keetha N, Mishra A, Karhade J, Jatavallabhula M, Scherer S, Krishna M, et al. AnyLoc: Towards universal visual place recognition. arXiv:2308.00688. 2023.10.1109/LRA.2023.3343602 ↗
8. Bags of binary words for fast place recognition in image sequences10.1109/TRO.2012.2197158 ↗
9. Large-scale image retrieval with compressed fisher vectors
10. Aggregating local image descriptors into compact codes10.1109/TPAMI.2011.235 ↗
11. MixVPR: feature mixing for visual place recognition
12. TransVPR: transformer-based place recognition with multi-level attention aggregation
13. Deformable kernels: adapting effective receptive fields for object deformation
14. Dynamic convolution: attention over convolution kernels
15. End-to-end learning of deep visual representations for image retrieval
16. FaceNet: a unified embedding for face recognition and clustering
17. Beyond triplet loss: a deep quadruplet network for person re-identification
18. Rethinking visual geo-localization for large-scale applications
19. CosFace: large margin cosine loss for deep face recognition
20. Visual place recognition with repetitive structures
21. Benchmarking 6DOF outdoor visual localization in changing conditions
22. Distance-ranking-based weighted triplet loss for visual place recognition
23. End-to-end image feature extraction-aggregation loop closure detection network for visual SLAM
24. Patch-NetVLAD: multi-scale fusion of locally-global descriptors for place recognition
25. Fine-tuning CNN image retrieval with no human annotation10.1109/TPAMI.2018.2846566 ↗
26. Hierarchical scene coordinate classification and regression for visual localization
27. Semantic-guided de-attention with sharpened triplet marginal loss for visual place recognition10.1016/j.patcog.2023.109645 ↗
28. Liu B, Wang Y, Tao H, Huang T, Tang F, Wu Y, et al. NocPlace: nocturnal visual place recognition via generative and inherited knowledge transfer. arXiv:2402.17159. 2024.