mlsanityData to 7 Oct 2026

Self-Supervised Learning for Place Representation Generalization across Appearance Changes

arXiv 2303.02370 ↗First posted 4 Mar 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Visual place recognition is a key to unlocking spatial navigation for animals, humans and robots. While state-of-the-art approaches are trained in a supervised manner and therefore hardly capture the information needed for generalizing to unusual conditions, we argue that self-supervised learning may help abstracting the place representation so that it can be foreseen, irrespective of the conditions. More precisely, in this paper, we investigate learning features that are robust to appearance modifications while sensitive to geometric transformations in a self-supervised manner. This dual-purpose training is made possible by combining the two self-supervision main paradigms, textiti.e. contrastive and predictive learning. Our results on standard benchmarks reveal that jointly learning such appearance-robust and geometry-sensitive image descriptors leads to competitive visual place recognition results across adverse seasonal and illumination conditions, without requiring any human-annotated labels.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 40 of its 68 references that are in the map. First posted on arXiv 4 Mar 2023.

Builds on

40 of 68 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  10. 2016Colorful Image Colorizationcited by 1,113
  11. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  12. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
28 more
  1. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  2. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  3. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 236
  4. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  5. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  6. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  7. 2020Self-supervising Fine-grained Region Similarities for Large-scale Image Localizationcited by 110
  8. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  9. 2021Where is your place, Visual Place Recognition?cited by 82
  10. 2015On the Performance of ConvNet Features for Place Recognitioncited by 72
  11. 2017Learnable pooling with Context Gating for video classificationcited by 58
  12. 2020Benchmarking Image Retrieval for Visual Localizationcited by 42
  13. 2023Self-supervised learning of Split Invariant Equivariant representationscited by 41
  14. 2022Unsupervised Learning of Group Invariant and Equivariant Representationscited by 38
  15. 2018Single-View Place Recognition under Seasonal Changescited by 35
  16. 2020On Compositions of Transformations in Contrastive Self-Supervised Learningcited by 34
  17. 2014Convolutional Neural Network-based Place Recognitioncited by 32
  18. 2018Lightweight Unsupervised Deep Loop Closurecited by 32
  19. 2021Residual Relaxation for Multi-view Representation Learningcited by 30
  20. 2022Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmarkcited by 27
  21. 2020Hierarchical Multi-Process Fusion for Visual Place Recognitioncited by 24
  22. 2019Condition-Invariant Multi-View Place Recognitioncited by 18
  23. 2022Leveraging Equivariant Features for Absolute Pose Regressioncited by 17
  24. 2022Equivariance and Invariance Inductive Bias for Learning from Insufficient Datacited by 14
  25. 2015Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detectioncited by 12
  26. 2021MegLoc: A Robust and Accurate Visual Localization Pipelinecited by 10
  27. 2021ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasetscited by 9
  28. 2018Deep Architectures and Ensembles for Semantic Video Classificationcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?cited by 5
  2. 2025How PARTs assemble into wholes: Learning the relative composition of imagescited by 2
  3. 2024An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstructioncited by 0
  4. 2025The Overlooked Value of Test-time Reference Sets in Visual Place Recognitioncited by 0