A Strong Baseline For Vehicle Re-identification
This repo is developed for Strong Baseline For Vehicle Re-Identification in Track 2 Ai-City-2021 Challenges
Our proposed method sheds light on three main factors that contribute most to the performance, including:
- Minizing the gap between real and synthetic data
- Network modification by stacking multi heads with attention mechanism to backbone
- Adaptive loss weight adjustment.
Our method achieves 61.34% mAP on the private CityFlow testset without using external dataset or pseudo labeling, and outperforms all previous works at 87.1% mAP on the Veri benchmark.
- apex (optional for FP16 training, if you don't have apex installed, please turn-off FP16 training by setting SOLVER.FP16=False)
$ git clone https://github.com/NVIDIA/apex $ cd apex $ pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
III. REPRODUCE THE RESULT ON AICITY 2020 CHALLENGE
Prepare training data
Convert the original synthetic images into more realistic one, using Unit repository
Using Mask-RCNN (pre-train on COCO) to extract foreground (car) and background, then we swap the foreground and background between training images.
Train multiple models using 3 different backbones: ResNext101_ibn, Resnet50_ibn, Resnet152
- Orientation ReID
- Camera ReID
1. Comparison with state-of-the art methods on VeRi776
- Download the checkpoint