mlsanityData to 7 Oct 2026

Working hard to know your neighbor's margins: Local descriptor learning loss

arXiv 1705.10872 ↗First posted 30 May 2017cs.CVcited by 212

Not on the map. Why?

Abstract (arXiv)

We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods; it works well for both shallow and deep convolution network architectures. Applying the novel loss to the L2Net CNN architecture results in a compact descriptor -- it has the same dimensionality as SIFT (128) that shows state-of-art performance in wide baseline stereo, patch verification and instance retrieval benchmarks. It is fast, computing a descriptor takes about 1 millisecond on a low-end GPU.

Key facts. Cited by 212 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 48; 2022: 33; 2023: 45; 2024: 26; 2025: 32; 2026: 28.

212 papers.

Sort:

By area:

  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  2. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  3. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  4. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  5. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  6. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  7. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  8. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  9. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  10. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  11. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  12. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
38 more
  1. 2024GIM: Learning Generalizable Image Matcher From Internet Videoscited by 72
  2. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  3. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  4. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  5. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  6. 2022Correlation Verification for Image Retrievalcited by 47
  7. 2021Progressive Correspondence Pruning by Consensus Learningcited by 46
  8. 2021SOLD2: Self-supervised Occlusion-aware Line Description and Detectioncited by 45
  9. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  10. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  11. 2025MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Trainingcited by 40
  12. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  13. 2022BALF: Simple and Efficient Blur Aware Local Feature Detectorcited by 34
  14. 2024Data curation via joint example selection further accelerates multimodal learningcited by 32
  15. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  16. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  17. 2022Decoupling Makes Weakly Supervised Local Feature Bettercited by 28
  18. 2023SFD2: Semantic-guided Feature Detection and Descriptioncited by 28
  19. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  20. 2022ReDFeat: Recoupling Detection and Description for Multimodal Feature Learningcited by 26
  21. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  22. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  23. 2025MP-SfM: Monocular Surface Priors for Robust Structure-from-Motioncited by 25
  24. 2021Deep learning-based person re-identification methods: A survey and outlook of recent workscited by 23
  25. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  26. 2022SealID: Saimaa ringed seal re-identification datasetcited by 22
  27. 2021NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learningcited by 21
  28. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
  29. 2022ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinementcited by 18
  30. 2023Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learningcited by 18
  31. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  32. 2021DFM: A Performance Baseline for Deep Feature Matchingcited by 17
  33. 2023(LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognitioncited by 16
  34. 2023FocusTune: Tuning Visual Localization through Focus-Guided Samplingcited by 16
  35. 2023Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypointscited by 15
  36. 2023Segment Anything Model is a Good Teacher for Local Feature Learningcited by 15
  37. 2021Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localizationcited by 14
  38. 2021Contextual Similarity Aggregation with Self-attention for Visual Re-rankingcited by 14

50 most cited of 212 All 212 (JSON)