# Decoupling Makes Weakly Supervised Local Feature Better

arXiv: https://arxiv.org/abs/2201.02861 · HTML: https://mlsanity.com/paper/2201.02861/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 8 Jan 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters](https://mlsanity.com/paper/1904.00889/) (2019)
- [Learning Feature Descriptors using Camera Pose Supervision](https://mlsanity.com/paper/2004.13324/) (2020)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)
- [Learning to Match Features with Seeded Graph Matching Network](https://mlsanity.com/paper/2108.08771/) (2021)
- [Dual-Resolution Correspondence Networks](https://mlsanity.com/paper/2006.08844/) (2020)
- [ContextDesc: Local Descriptor Augmentation with Cross-Modality Context](https://mlsanity.com/paper/1904.04084/) (2019)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [Online Invariance Selection for Local Feature Descriptors](https://mlsanity.com/paper/2007.08988/) (2020)
- [Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task](https://mlsanity.com/paper/1912.00623/) (2019)
- [Parallax Attention for Unsupervised Stereo Correspondence Learning](https://mlsanity.com/paper/2009.08250/) (2020)
- [Quad-networks: unsupervised learning to rank for interest point detection](https://mlsanity.com/paper/1611.07571/) (2016)
- [Beyond Cartesian Representations for Local Descriptors](https://mlsanity.com/paper/1908.05547/) (2019)

## Built on by (most cited first, 28 of 28)

- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [PATS: Patch Area Transportation with Subdivision for Local Feature Matching](https://mlsanity.com/paper/2303.07700/) (2023)
- [SFD2: Semantic-guided Feature Detection and Description](https://mlsanity.com/paper/2304.14845/) (2023)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [Learning Rotation-Equivariant Features for Visual Correspondence](https://mlsanity.com/paper/2303.15472/) (2023)
- [Segment Anything Model is a Good Teacher for Local Feature Learning](https://mlsanity.com/paper/2309.16992/) (2023)
- [SACReg: Scene-Agnostic Coordinate Regression for Visual Localization](https://mlsanity.com/paper/2307.11702/) (2023)
- [DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection](https://mlsanity.com/paper/2503.07347/) (2025)
- [RDD: Robust Feature Detector and Descriptor using Deformable Transformer](https://mlsanity.com/paper/2505.08013/) (2025)
- [Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matching](https://mlsanity.com/paper/2305.00194/) (2023)
- [EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching](https://mlsanity.com/paper/2502.20685/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [SRPose: Two-view Relative Pose Estimation with Sparse Keypoints](https://mlsanity.com/paper/2407.08199/) (2024)
- [PRISM: PRogressive dependency maxImization for Scale-invariant image Matching](https://mlsanity.com/paper/2408.03598/) (2024)
- [Learning Affine Correspondences by Integrating Geometric Constraints](https://mlsanity.com/paper/2504.04834/) (2025)
- [Shared Coupling-bridge for Weakly Supervised Local Feature Learning](https://mlsanity.com/paper/2212.07047/) (2022)
- [RaCo: Ranking and Covariance for Practical Learned Keypoints](https://mlsanity.com/paper/2602.15755/) (2026)
- [PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models](https://mlsanity.com/paper/2507.08400/) (2025)
- [A Streamlined Attention-Based Network for Descriptor Extraction](https://mlsanity.com/paper/2601.13126/) (2026)
- [Local Feature Extraction from Salient Regions by Feature Map Transformation](https://mlsanity.com/paper/2301.10413/) (2023)
- [LGFCTR: Local and Global Feature Convolutional Transformer for Image Matching](https://mlsanity.com/paper/2311.17571/) (2023)
- [GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy](https://mlsanity.com/paper/2604.05359/) (2026)
- [DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization](https://mlsanity.com/paper/2212.04575/) (2022)
- [Self-supervised Training Sample Difficulty Balancing for Local Descriptor Learning](https://mlsanity.com/paper/2303.06124/) (2023)
- [Camera Agnostic Two-Head Network for Ego-Lane Inference](https://mlsanity.com/paper/2404.12770/) (2024)
- [From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection](https://mlsanity.com/paper/2602.20630/) (2026)
- [RIPE++: Reinforced Keypoint Learning from Positive Pairs Only](https://mlsanity.com/paper/2608.19693/) (2026)

## 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.