mlsanityData to 7 Oct 2026

Decoupling Makes Weakly Supervised Local Feature Better

arXiv 2201.02861 ↗First posted 8 Jan 2022cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the detection and description steps, directly conducting weakly supervised learning within a joint describe-then-detect pipeline suffers limited performance. In this paper, we propose a decoupled describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning. Extensive experiments show that our method, namely PoSFeat (Camera Pose Supervised Feature), outperforms previous fully and weakly supervised methods and achieves state-of-the-art performance on a wide range of downstream tasks.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 8 Jan 2022.

Builds on

34 of 60 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  4. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  7. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2020DISK: Learning local features with policy gradientcited by 310
  10. 2016LIFT: Learned Invariant Feature Transformcited by 305
  11. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  12. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
22 more
  1. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  2. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  3. 2018LF-Net: Learning Local Features from Imagescited by 151
  4. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  5. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  6. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 128
  7. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  8. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  9. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  10. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  11. 2020Dual-Resolution Correspondence Networkscited by 90
  12. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  13. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  14. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  15. 2019Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Taskcited by 39
  16. 2020Parallax Attention for Unsupervised Stereo Correspondence Learningcited by 39
  17. 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
  18. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  19. 2019UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptorcited by 22
  20. 2021RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matchingcited by 19
  21. 2020Image Stylization for Robust Featurescited by 11
  22. 2019GSLAM: A General SLAM Framework and Benchmarkcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 5; 2025: 6; 2026: 5.

28 papers.

Sort:

  1. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  2. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  3. 2023SFD2: Semantic-guided Feature Detection and Descriptioncited by 28
  4. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  5. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25
  6. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  7. 2023Segment Anything Model is a Good Teacher for Local Feature Learningcited by 15
  8. 2023SACReg: Scene-Agnostic Coordinate Regression for Visual Localizationcited by 14
  9. 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformercited by 13
  10. 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 12
  11. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  12. 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matchingcited by 7
16 more
  1. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  2. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  3. 2024PRISM: PRogressive dependency maxImization for Scale-invariant image Matchingcited by 5
  4. 2025Learning Affine Correspondences by Integrating Geometric Constraintscited by 5
  5. 2022Shared Coupling-bridge for Weakly Supervised Local Feature Learningcited by 4
  6. 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
  7. 2025PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Modelscited by 2
  8. 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2
  9. 2023Local Feature Extraction from Salient Regions by Feature Map Transformationcited by 1
  10. 2023LGFCTR: Local and Global Feature Convolutional Transformer for Image Matchingcited by 1
  11. 2026GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergycited by 1
  12. 2022DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localizationcited by 0
  13. 2023Self-supervised Training Sample Difficulty Balancing for Local Descriptor Learningcited by 0
  14. 2024Camera Agnostic Two-Head Network for Ego-Lane Inferencecited by 0
  15. 2026From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detectioncited by 0
  16. 2026RIPE++: Reinforced Keypoint Learning from Positive Pairs Onlycited by 0