DELG-pytorch

Pytorch Implementation of Unifying Deep Local and Global Features for Image Search (delg-eccv20)

DELG pipline:

Installation

Install Python dependencies:

pip install -r requirements.txt

Set PYTHONPATH:

export PYTHONPATH=`pwd`:$PYTHONPATH

Training

Training a delg model:

python train_delg.py \
    --cfg configs/metric/resnet_delg_8gpu.yaml \
    OUT_DIR ./output \
    PORT 12001 \
    TRAIN.WEIGHTS path/to/pretrainedmodel

Resume training:

python train_delg.py \
    --cfg configs/metric/resnet_delg_8gpu.yaml \
    OUT_DIR ./output \
    PORT 12001 \
    TRAIN.AUTO_RESUME True

Weights

-r50-delg (wu46)

-r101-delg (5pdj)

pretrained weeights are available in pymetric

Feature extraction

!!! Queries should be cropped as DOLG.

Extracting global and local feature for multi-scales

python tools/extractor.py --cfg configs/resnet_delg_8gpu.yaml

Refer extractor.sh for using multicards

See visualize.ipynb for verification of local features

Evaluation on ROxf and RPar

Local Match

Spatial Verification

Install pydegensac and see tools/rerank/spatial_verification.py
Examples

ASMK

(https://github.com/jenicek/asmk)

Results

See (https://github.com/filipradenovic/revisitop) for details

cd tools/revisitop
python example_evaluate_with_local.py main

on roxford5k

| Backbone | Train Size | Method | mAP E | mAP M | mAP H | |--------------|:-------:|:------:|:-------:|:------------:|:-------------:| | ResNet50 | 224 | Global Ranking | 77.73 | 66.06 | 38.37 | | ResNet50 | 224 | Global | 81.03 | 68.31 | 39.98 | | ResNet50 | 224 | Global + Spatial Verification | 84.81 | 71.97 | 46.63 | | ResNet50 | 512 | Global | 90.55 | 78.51 | 56.90 | | ResNet50 | 512 | Global + Spatial Verification | 90.86 | 80.08 | 58.42 |

on rparis6k(updating)

SOTA of R50-DELG is 78.3 mAP@M in the paper, we outperform it
All training set version is GLDv2-clean (81313, 1580470)
Traing size, global and local feature scales adopted are same with the paper

DELG

Install / Use

README