From 085d21f9f86d05046825532b341116ae0607315b Mon Sep 17 00:00:00 2001
From: tsingcbx99 <57670068+tsingcbx99@users.noreply.github.com>
Date: Wed, 3 Aug 2022 16:07:53 +0800
Subject: [PATCH] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index a0f5c528..afa9c196 100644
--- a/README.md
+++ b/README.md
@@ -9,6 +9,8 @@ the following methods:
 - Pre-trained Model Selection [[Code]](/examples/model_selection) [[API]](/tllib/ranking)
 - Semi-supervised Learning for Classification [[Code]](/examples/semi_supervised_learning/image_classification/) [[API]](/tllib/self_training)
 
+Besides, we maintain a collection of **_awesome papers in Transfer Learning_** in another repo [_A Roadmap for Transfer Learning_](https://github.com/thuml/A-Roadmap-for-Transfer-Learning).
+
 ### 2022.2
 We adjusted our API following our survey [Transferablity in Deep Learning](https://arxiv.org/abs/2201.05867).
 
@@ -30,7 +32,6 @@ _examples_ is still divided by learning setup.
 
 ## Introduction
 *TLlib* is an open-source and well-documented library for Transfer Learning. It is based on pure PyTorch with high performance and friendly API. Our code is pythonic, and the design is consistent with torchvision. You can easily develop new algorithms, or readily apply existing algorithms.
-Besides, we maintain a collection of awesome papers in Transfer Learning in another repo [A Roadmap for Transfer Learning](https://github.com/thuml/A-Roadmap-for-Transfer-Learning).
 
 The currently supported algorithms include: