Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-cbir-papers
📝Awesome and classical image retrieval papers
https://github.com/willard-yuan/awesome-cbir-papers
Last synced: about 3 hours ago
JSON representation
-
Classical Local Feature
- Visual Categorization with Bags of Keypoints
- ORB: an efficient alternative to SIFT or SURF
- Three things everyone should know to improve object retrieval
- On-the-fly learning for visual search of large-scale image and video datasets
- All about VLAD
- Aggregating localdescriptors into a compact image representation
- More About VLAD: A Leap from Euclidean to Riemannian Manifolds
- Hamming embedding and weak geometric consistency for large scale image search
- Revisiting the VLAD image representation
- Improving the Fisher Kernel for Large-Scale Image Classification
- Image Classification with the Fisher Vector: Theory and Practice
- A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval
- Triangulation embedding and democratic aggregation for image search
- Efficient Large-scale Image Search With a Vocabulary Tree
- Object retrieval with large vocabularies and fast spatial matching
-
Deep Learning Feature (Global Feature)
- Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
- SOLAR: Second-Order Loss and Attention for Image Retrieval
- Unifying Deep Local and Global Features for Image Search
- SOLAR: Second-Order Loss and Attention for Image Retrieval
- A Benchmark on Tricks for Large-scale Image Retrieval
- Learning with Average Precision: Training Image Retrieval with a Listwise Loss
- MultiGrain: a unified image embedding for classes and instances
- End-to-end Learning of Deep Visual Representations for Image retrieval
- What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
- Cross-dimensional Weighting for Aggregated Deep Convolutional Features
- Aggregating Deep Convolutional Features for Image Retrieval
- Particular object retrieval with integral max-pooling of CNN activations
- Learning to Match Aerial Images with Deep Attentive Architectures
- Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval
- Combining Fisher Vector and Convolutional Neural Networks for Image Retrieval
- Selective Deep Convolutional Features for Image Retrieval
- Fine-tuning CNN Image Retrieval with No Human Annotation
- An accurate retrieval through R-MAC+ descriptors for landmark recognition
- Regional Attention Based Deep Feature for Image Retrieval - RegionalAttention), BMVC 2018.
- Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
- Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
- Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
- Learning with Average Precision: Training Image Retrieval with a Listwise Loss
- Bags of Local Convolutional Features for Scalable Instance Search
- SOLAR: Second-Order Loss and Attention for Image Retrieval
- Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
-
Deep Learning Feature (Local Feature)
- LightGlue: Local Feature Matching at Light Speed
- Simple Learned Keypoints - supervised deep learning keypoint model, arxiv 2023, [code](https://github.com/facebookresearch/silk).
- Learning Super-Features for Image Retrieval
- LoFTR: Detector-Free Local Feature Matching with Transformers
- DFM: A Performance Baseline for Deep Feature Matching
- Learning and aggregating deep local descriptors for instance-level recognition
- DISK: Learning local features with policy gradient - epfl/disk).
- Learning and aggregating deep local descriptorsfor instance-level recognition
- D2D: Keypoint Extraction with Describe to Detect Approach
- UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision
- Visualizing Deep Similarity Networks
- Beyond Cartesian Representations for Local Descriptors - epfl/log-polar-descriptors), ICCV 2019.
- R2D2: Reliable and Repeatable Detector and Descriptor
- Local Features and Visual Words Emerge in Activations
- Explicit Spatial Encoding for Deep Local Descriptors
- Learning Discriminative Affine Regions via Discriminability - aiki/affnet).
- A Large Dataset for Improving Patch Matching - Dataset](https://github.com/rmitra/PS-Dataset).
- LF-Net: Learning Local Features from Images
- Local Descriptors Optimized for Average Precision
- SuperPoint: Self-Supervised Interest Point Detection and Description
- GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
- DISK: Learning local features with policy gradient - epfl/disk).
- LightGlue: Local Feature Matching at Light Speed
- Online Invariance Selection for Local Feature Descriptors
- Local Descriptors Optimized for Average Precision
- D2D: Keypoint Extraction with Describe to Detect Approach
-
Deep Learning Feature (Instance Search)
-
ANN search
- Results of the NeurIPS’21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
- Nearest neighbor search with compact codes: A decoder perspective
- Accelerating Large-Scale Inference with Anisotropic Vector Quantization - scann-efficient-vector.html), [code](https://github.com/google-research/google-research/tree/master/scann), ICML 2020.
- Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination
- RobustiQ A Robust ANN Search Method for Billion-scale Similarity Search on GPUs
- Zoom: Multi-View Vector Search for Optimizing Accuracy, Latency and Memory
- Vector and Line Quantization for Billion-scale Similarity Search on GPUs
- Learning to Route in Similarity Graphs
- Polysemous codes
- Optimized Product Quantization
- Fast Approximate Nearest Neighbor Search With Navigating Spreading-out Graphs
- Efficient Nearest Neighbors Search for Large-Scale Landmark Recognition
- NV-tree: A Scalable Disk-Based High-Dimensional Index
- Dynamicity and Durability in Scalable Visual Instance Search
- Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors - hnsw).
- Link and code: Fast indexing with graphs and compact regression codes
- A Survey of Product Quantization
- GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
- Learning a Complete Image Indexing Pipeline
- spreading vectors for similarity search
- A Survey of Product Quantization
- Vector and Line Quantization for Billion-scale Similarity Search on GPUs
-
CBIR Attack
-
CBIR rank
- Fast Spectral Ranking for Similarity Search - aiki/manifold-diffusion), CVPR 2018.
- Fast Spectral Ranking for Similarity Search - aiki/manifold-diffusion), CVPR 2018.
-
CBIR in Industry
- Videntifier - scale local feature database, [demo](http://flickrdemo.videntifier.com/), based on SIFT feature and NV-tree. ([Chinese blog post](https://yongyuan.name/blog/videntifier-and-nv-tree.html)).
- Web-Scale Responsive Visual Search at Bing
- Visual Search at Pinterest
- Visual Discovery at Pinterest
- Learning a Unified Embedding for Visual Search at Pinterest
- Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce - incubator/fk-visual-search).
- 微信「扫一扫识物」 的背后技术揭秘
- 揭秘微信「扫一扫」识物为什么这么快?
- Visual Search at Alibaba
- Videntifier - scale local feature database, [demo](http://flickrdemo.videntifier.com/), based on SIFT feature and NV-tree. ([Chinese blog post](https://yongyuan.name/blog/videntifier-and-nv-tree.html)).
-
CBIR Competition and Challenge
- The 2021 Image Similarity Dataset and Challenge
- Google Landmark Retrieval Challenge
- Alibaba Large-scale Image Search Challenge
- Pkbigdata image retrieval
- Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset - 1st-and-3rd-Place-Solution](https://github.com/lyakaap/Landmark2019-1st-and-3rd-Place-Solution).
- The 2021 Image Similarity Dataset and Challenge
- Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset - 1st-and-3rd-Place-Solution](https://github.com/lyakaap/Landmark2019-1st-and-3rd-Place-Solution).
-
CBIR for Duplicate(copy) detection
-
Instance Matching
- Neural- Guided RANSAC: Learning Where to Sample Model Hypotheses
- AdaLAM: Revisiting Handcrafted Outlier Detection
- Graph-Cut RANSAC - cut-ransac)
- Image Matching Benchmark
- Robust feature matching in 2.3µs
- openMVG robust_estimation
- Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses
- Homography from two orientation- and scale-covariant features - from-sift-features).
- Homography from two orientation- and scale-covariant features - from-sift-features).
- Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses
-
Template Matching
-
Image Identification
-
Tutorials
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- Compact Features for Visual Search
- Image Similarity using Deep Ranking - similarity-deep-ranking).
- Triplet Loss and Online Triplet Mining in TensorFlow
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
- How to Apply Distance Metric Learning to Street-to-Shop Problem
-
Slide
-
Demo and Demo Online
- Visual Image Retrieval and Localization
- yisou - based painting cbir system, the search algorithm is designed by [Yong Yuan](http://yongyuan.name/).
-
Datasets
- Holidays
- Oxford
- Paris
- ROxford and RParis
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
- Holidays
-
Useful Package
-
Star History
- ![Star History Chart - history.com/#willard-yuan/awesome-cbir-papers&Date)
Categories
Datasets
36
Tutorials
28
Deep Learning Feature (Local Feature)
26
Deep Learning Feature (Global Feature)
26
ANN search
22
Classical Local Feature
15
Instance Matching
10
CBIR in Industry
10
CBIR Competition and Challenge
7
Deep Learning Feature (Instance Search)
4
CBIR rank
2
CBIR for Duplicate(copy) detection
2
Demo and Demo Online
2
Useful Package
2
Image Identification
1
CBIR Attack
1
Slide
1
Star History
1
Template Matching
1
Sub Categories