[Arxiv] [知乎]

By Wuyang Li

Welcome to have a look at our previous work SCAN (AAAI'22 ORAL), which is the foundation of this work.

Check INSTALL.md for installation instructions.

If you have any problem in terms of installation, feel free to screenshot your issue for me. Thanks.

Step 1: Format three benchmark datasets. (BDD100k is also available)

[DATASET_PATH]
└─ Cityscapes
   └─ cocoAnnotations
   └─ leftImg8bit
      └─ train
      └─ val
   └─ leftImg8bit_foggy
      └─ train
      └─ val
└─ KITTI
   └─ Annotations
   └─ ImageSets
   └─ JPEGImages
└─ Sim10k
   └─ Annotations
   └─ ImageSets
   └─ JPEGImages

Step 2: change the data root for your dataset at paths_catalog.py.

DATA_DIR = [$Your dataset root]

More detailed dataset preparation can be found at EPM.

1. We provide super detailed code comments in sigma_vgg16_cityscapace_to_foggy.yaml. We strongly recommend you to have a look.
2. We modify the trainer to meet the requirements of SIGMA.
3. GM is integrated in this "middle layer" graph_matching_head.
4. Node sampling is conducted in here.
5. We preserve lots of APIs for many implementation choices in here
6. We hope this work can inspire lots of good ideas

We have provided lots of well-trained models at (onedrive).

1. Kindly note that it is easy to get higher results than the reported ones with tailor-tuned hyperparameters.
2. We didn't tune the hyperparameters for ResNet-50, and it could be further improved.
3. We have tested on C2F and S2F with end-to-end training, finding it can also achieve SOTA results, as mentioned in our appendix.
4. After correcting a default hyper-parameter, our S2C gives four mAP gains compared with the reported one, as explained in the config file.

Train the model from the scratch

python tools/train_net_da.py \
        --config-file configs/SIGMA/xxx.yaml \

Test the well-trained model

python tools/test_net.py \
        --config-file configs/SIGMA/xxx.yaml \
        WEIGHT 'well_trained_models/xxx.pth'

If you think this work is helpful for your project, please give it a star and citation:

@inproceedings{li2022sigma,
  title={SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection},
  author={Li, Wuyang and Liu, Xinyu and Yuan, Yixuan},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}

E-mail: wuyangli2-c@my.cityu.edu.hk

This work is based on SCAN (AAAI'22 ORAL) and EPM (ECCV20).

The implementation of our anchor-free detector is from FCOS.

Domain Adaptive Object Detection (DAOD) leverages a labeled source domain to learn an object detector generalizing to a novel target domain free of annotations. Recent advances align class-conditional distributions through narrowing down cross-domain prototypes (class centers). Though great success, these works ignore the significant within-class variance and the domain-mismatched semantics within the training batch, leading to a sub-optimal adaptation. To overcome these challenges, we propose a novel SemantIc-complete Graph MAtching (SIGMA) framework for DAOD, which completes mismatched semantics and reformulates the adaptation with graph matching. Specifically, we design a Graph-embedded Semantic Completion module (GSC) that completes mismatched semantics through generating hallucination graph nodes in missing categories. Then, we establish cross-image graphs to model class-conditional distributions and learn a graph-guided memory bank for better semantic completion in turn. After representing the source and target data as graphs, we reformulate the adaptation as a graph matching problem, i.e., finding well-matched node pairs across graphs to reduce the domain gap, which is solved with a novel Bipartite Graph Matching adaptor (BGM). In a nutshell, we utilize graph nodes to establish semantic-aware node affinity and leverage graph edges as quadratic constraints in a structure-aware matching loss, achieving fine-grained adaptation with a node-to-node graph matching. Extensive experiments demonstrate that our method outperforms existing works significantly.