你确认删除该任务么?此任务一旦删除不可恢复。
zhaijianyang ead6340af6 | 2 年前 | |
---|---|---|
data/usps | 2 年前 | |
.gitignore | 2 年前 | |
ASPC.py | 2 年前 | |
MyModel.py | 2 年前 | |
README.md | 2 年前 | |
datasets.py | 2 年前 | |
metrics.py | 2 年前 | |
run_exp.py | 2 年前 |
Tensorflow implementation for our paper:
Deep clustering gains superior performance than conventional clustering by jointly performing feature learning and cluster
assignment. Although numerous deep clustering algorithms have emerged in various applications, most of them fail to learn robust
cluster-oriented features which in turn hurts the final clustering performance. To solve this problem, we propose a two-stage deep
clustering algorithm by incorporating data augmentation and self-paced learning. Specifically, in the first stage, we learn robust features
by training an autoencoder with examples that are augmented by random shifting and rotating the given clean examples. Then in the
second stage, we encourage the learned features to be cluster-oriented by alternatively finetuning the encoder with the augmented
examples and updating the cluster assignments of the clean examples. During finetuning the encoder, the target of each augmented
example in the loss function is the center of the cluster to which the clean example is assigned. The targets may be computed
incorrectly, and the examples with incorrect targets could mislead the encoder network. To stabilize the network training, we select
most confident examples in each iteration by utilizing the adaptive self-paced learning. Extensive experiments validate that our
algorithm outperforms the state of the arts on four image datasets.
Install Anaconda with Python 3.6 version (Optional).
Create a new env (Optional):
conda create -n aspc python=3.6 -y
source activate aspc # Linux
# or
conda activate aspc # Windows
Install required packages:
pip install tensorflow-gpu==1.10 scikit-learn h5py
git clone https://github.com/XifengGuo/ASPC-DA.git ASPC-DA
cd ASPC-DA
python run_exp.py
Adaptive Self-paced Deep Clustering with Data Augmentation
Python
尊敬的启智用户
感谢您一直以来对Openl启智社区AI协作平台的支持。为了保障您的使用权益和确保网络安全,我们于2024年1月份更新了《Openl启智社区AI协作平台使用协议》。更新后的协议明确了用户禁止使用内网穿透工具的条例。您单击“同意并继续”后,便可以继续使用我们的服务。感谢您的合作与理解。
更多协议内容,请参考《Openl启智社区AI协作平台使用协议》