2020-05-29 16:23:55 +08:00
# SCDA_pytorch
A pytorch implementation of the "Selective Convolutional Descriptor Aggregation" algorithm
2020-05-29 19:20:21 +08:00
## NOTE
cpu-only version
2020-05-31 10:27:41 +08:00
no in [1]
```
train_data_L31a(i,:) = train_data_L31a(i,:) ./ norm(train_data_L31a(i,:));
```
2020-05-29 19:20:21 +08:00
[largestConnectComponent ](https://blog.csdn.net/xuyangcao123/article/details/81023732 )
## Details
2020-05-29 19:32:34 +08:00
install requirements
```
pip install -r requirements.txt;
```
2020-05-31 10:27:41 +08:00
On CUB and split dataset in `CUB_200.py` .
2020-05-29 19:20:21 +08:00
random split CUB-200-2011 results:
||top1|top5
---|:--:|---:
2020-05-31 10:27:41 +08:00
CUB|0.46|0.71
2020-05-29 19:32:34 +08:00
2020-05-31 10:27:41 +08:00
>[1] Wei X S , Luo J H , Wu J , et al. Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval[J]. IEEE Transactions on Image Processing, 2017, 26(6):2868-2881.
