This is the official PyTorch implementation of our paper:
Tackling Background Distraction in Video Object Segmentation, ECCV 2022
Suhwan Cho, Heansung Lee, Minhyeok Lee, Chaewon Park, Sungjun Jang, Minjung Kim, Sangyoun Lee
Link: [ECCV] [arXiv]
You can also find other related papers at awesome-video-object-segmentation.
In semi-supervised VOS, one of the main challenges is the existence of background distractors that have a similar appearance to the target objects. As comparing visual properties is a fundamental technique, visual distractions can severely lower the reliability of a system. To suppress the negative influence of background distractions, we propose three novel strategies: 1) a spatio-temporally diversified template construction scheme to prepare various object properties for reliable and stable prediction; 2) a learnable distance-scoring function to consider the temporal consistency of a video; 3) swap-and-attach data augmentation to provide hard training samples showing severe occlusions.
1. Download COCO, DAVIS, and YouTube-VOS from the official websites.
2. Download our custom split for the YouTube-VOS training set.
3. Replace dataset paths in "run.py" file with your dataset paths.
1. Open the "run.py" file.
2. Verify the training settings.
3. Start TBD training!
python run.py --train
1. Open the "run.py" file.
2. Choose a pre-trained model.
3. Start TBD testing!
python run.py --test
pre-trained model (davis)
pre-trained model (ytvos)
pre-computed results
Code and models are only available for non-commercial research purposes.
If you have any questions, please feel free to contact me :)
E-mail: suhwanx@gmail.com