Update README

README.md

@@ -90,8 +90,6 @@ python run_lamda.py 1 dslr amazon format csv num_iters 20000 sumary_freq 400 le
 python run_lamda.py 1 webcam amazon format csv num_iters 20000 summary_freq 400 learning_rate 0.0001 inorm True batch_size 310 src_class_trade_off 1.0 domain_trade_off 0.1 src_vat_trade_off 1.0 trg_trade_off 0.1 save_grads False cast_data False cnn_size small update_target_loss False m_on_D_trade_off 1.0 m_plus_1_on_D_trade_off 1.0 m_plus_1_on_G_trade_off 1.0 m_on_G_trade_off 1.0 data_path ""
 ```
 
-
-
 ## C. Results
 
 | Methods | **A** --> **W** | **A** --> **D** | **D** --> **W** | **W** --> **D** | **D** --> **A** | **W** --> **A** | Avg |
@@ -106,9 +104,32 @@ python run_lamda.py 1 webcam amazon format csv num_iters 20000 summary_freq 400
 | RWOT [8] | 95.1 | 94.5 | 99.5 | **100.0** | 77.5 | 77.9 | 90.8 |
 | **LAMDA** | **95.2** | **96.0** | 98.5 | **99.8** | **87.3** | **84.4** | **93.0** |
 
-## D. References
+## D. Citations
+
+If our code is helpful for your research, please cite our paper 
+
+```
+@InProceedings{pmlr-v139-le21a,
+ title = {LAMDA: Label Matching Deep Domain Adaptation},
+ author = {Le, Trung and Nguyen, Tuan and Ho, Nhat and Bui, Hung and Phung, Dinh},
+ booktitle = {Proceedings of the 38th International Conference on Machine Learning},
+ pages = {6043--6054},
+ year = {2021},
+ editor = {Meila, Marina and Zhang, Tong},
+ volume = {139},
+ series = {Proceedings of Machine Learning Research},
+ month = {18--24 Jul},
+ publisher = {PMLR},
+ pdf = {http:https://proceedings.mlr.press/v139/le21a/le21a.pdf},
+ url = {https://proceedings.mlr.press/v139/le21a.html},
+ abstract = {Deep domain adaptation (DDA) approaches have recently been shown to perform better than their shallow rivals with better modeling capacity on complex domains (e.g., image, structural data, and sequential data). The underlying idea is to learn domain invariant representations on a latent space that can bridge the gap between source and target domains. Several theoretical studies have established insightful understanding and the benefit of learning domain invariant features; however, they are usually limited to the case where there is no label shift, hence hindering its applicability. In this paper, we propose and study a new challenging setting that allows us to use a Wasserstein distance (WS) to not only quantify the data shift but also to define the label shift directly. We further develop a theory to demonstrate that minimizing the WS of the data shift leads to closing the gap between the source and target data distributions on the latent space (e.g., an intermediate layer of a deep net), while still being able to quantify the label shift with respect to this latent space. Interestingly, our theory can consequently explain certain drawbacks of learning domain invariant features on the latent space. Finally, grounded on the results and guidance of our developed theory, we propose the Label Matching Deep Domain Adaptation (LAMDA) approach that outperforms baselines on real-world datasets for DA problems.}
+}
+```
+
+
+## E. References
 
-### D.1. Baselines:
+### E.1. Baselines:
 
 [1] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
 
@@ -126,6 +147,6 @@ python run_lamda.py 1 webcam amazon format csv num_iters 20000 summary_freq 400
 
 [8] R. Xu, P. Liu, L. Wang, C. Chen, and J. Wang. Reliable weighted optimal transport for unsupervised domain adaptation. In CVPR 2020, June 2020.
 
-### D.2. GitHub repositories: 
+### E.2. GitHub repositories: 
 
 - Some parts of our code (e.g., VAT, evaluation, …) are rewritten with modifications from [DIRT-T](https://github.com/RuiShu/dirt-t).