DELF: DEep Local Features
This project presents code for extracting DELF features, which were introduced with the paper "Large-Scale Image Retrieval with Attentive Deep Local Features". A simple application is also illustrated, where two images containing the same landmark can be matched to each other, to obtain local image correspondences.
DELF is particularly useful for large-scale instance-level image recognition. It detects and describes semantic local features which can be geometrically verified between images showing the same object instance. The pre-trained model released here has been optimized for landmark recognition, so expect it to work well in this area. We also provide tensorflow code for building the DELF model, which could then be used to train models for other types of objects.
If you make use of this code, please consider citing:
"Large-Scale Image Retrieval with Attentive Deep Local Features", Hyeonwoo Noh, Andre Araujo, Jack Sim, Tobias Weyand, Bohyung Han, Proc. ICCV'17
- DELF achieved state-of-the-art results in a CVPR'18 image retrieval paper: Radenovic et al., "Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking".
- DELF was featured in ModelDepot
- DELF is now available in TF-Hub
The Google-Landmarks dataset has been released as part of two Kaggle challenges: Landmark Recognition and Landmark Retrieval. If you make use of the dataset in your research, please consider citing the paper mentioned above.
To be able to use this code, please follow these instructions to properly install the DELF library.
Quick start: DELF extraction and matching
Please follow these instructions. At the end, you should obtain a nice figure showing local feature matches, as:
DELF's code is located under the
delf directory. There are two directories
This directory contains three protobufs:
datum.proto: general-purpose protobuf for serializing float tensors.
feature.proto: protobuf for serializing DELF features.
delf_config.proto: protobuf for configuring DELF extraction.
This directory contains files for several different purposes:
feature_io.pyare helper files for reading and writing tensors and features.
delf_v1.pycontains the code to create DELF models.
feature_extractor.pycontains the code to extract features using DELF. This is particularly useful for extracting features over multiple scales, with keypoint selection based on attention scores, and PCA/whitening post-processing.
Besides these, other files in this directory contain tests for different modules.
delf/python/examples contains sample scripts to run DELF
feature extraction and matching:
extract_features.pyenables DELF extraction from a list of images.
match_images.pysupports image matching using DELF features extracted using
delf_config_example.pbtxtshows an example instantiation of the DelfConfig proto, used for DELF feature extraction.
André Araujo (@andrefaraujo)
October 26, 2017
Initial release containing DELF-v1 code, including feature extraction and matching examples.
Thanks to contributors: André Araujo, Hyeonwoo Noh, Youlong Cheng, Jack Sim.