Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
kaoyu d748710a11 | 2 years ago | |
---|---|---|
datasets | 2 years ago | |
models | 2 years ago | |
resrc | 2 years ago | |
README.md | 2 years ago | |
laboratory.py | 2 years ago | |
load_bbox.py | 2 years ago | |
main.py | 2 years ago | |
ops.py | 2 years ago | |
train.py | 2 years ago | |
utils.py | 2 years ago | |
validation.py | 2 years ago |
Official Pytorch implementation of "PsyNet: Self-supervised Approach to Object Localization Using Point Symmetric Transformation"
This implementation is based on these repos.
Pre-trained checkpoints are now available
This paper is accepted by AAAI 2020. The pdf is available at https://aaai.org/ojs/index.php/AAAI/article/view/6615/6469
Existing co-localization techniques significantly lose performance over weakly or fully supervised methods in accuracy and inference time. In this paper, we overcome common drawbacks of co-localization techniques by utilizing self-supervised learning approach. The major technical contributions of the proposed method are two-fold. 1) We devise a new geometric transformation, namely point symmetric transformation and utilize its parameters as an artificial label for self-supervised learning. This new transformation can also play the role of region-drop based regularization. 2) We suggest a heat map extraction method for computing the heat map from the network trained by self-supervision, namely class-agnostic activation mapping. It is done by computing the spatial attention map. Based on extensive evaluations, we observe that the proposed method records new state-of-the-art performance in three fine-grained datasets for unsupervised object localization. Moreover, we show that the idea of the proposed method can be adopted in a modified manner to solve the weakly supervised object localization task. As a result, we outperform the current state-of-the-art technique in weakly supervised object localization by a significant gap.
Project
|--- data
| |--- CUB
| |--- CUB_200_2011
| |--- images
| | |--- 200 directories (001.Black ... ~ 200.Common ...)
| |--- sizes.txt
|--- PsyNet
|--- models
| |--- networks.py
| |--- resnet.py
| |--- ...
|--- main.py
|--- train.py
| ...
python -W ignore main.py --dataset CUB --network vggcam16bn --tftypes OR
Checkpoints
Performance
How to load .ckpt (Pre-trained checkpoint)
python -W ignore main.py --gpu 5 --dataset CUB --network vggcam16bn --tftypes OR --validation --load_model CUB_VGG16BN
python -W ignore main.py --gpu 5 --dataset AIRCRAFT --network vggcam16bn --tftypes OR --validation --load_model Aircraft_VGG16BN
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》