图像质量评估（Image Quality Assessment, IQA）即评估图像的质量。

图像增强（Image Enhancement），其目的是要改善图像的视觉效果。

(CVPR 2016) Traffic-Sign Detection and Classification in the Wild

Paper: https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhu_Traffic-Sign_Detection_and_CVPR_2016_paper.pdf

Page: https://cg.cs.tsinghua.edu.cn/traffic-sign/

Code: http://cg.cs.tsinghua.edu.cn/traffic-sign/data_model_code/code.zip

(ICML 2018) Efficient Neural Architecture Search via Parameter Sharing

Paper: https://arxiv.org/abs/1802.03268

Code: https://github.com/melodyguan/enas

(CVPR 2018) Learning Transferable Architectures for Scalable Image Recognition

Paper: https://arxiv.org/abs/1707.07012

Page: https://ai.googleblog.com/2017/11/automl-for-large-scale-image.html

Code: https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet

(ICLR 2017) Neural Architecture Search with Reinforcement Learning

Paper: https://arxiv.org/abs/1611.01578

Page: https://ai.googleblog.com/2017/05/using-machine-learning-to-explore.html

参考 https://github.com/tensorflow/models/tree/master/research/attention_ocr

使用 TensorFlow Attention OCR API 进行图像文本提取

修改后的代码：https://github.com/lijiancheng0614/tensorflow_attention_ocr

参考 https://github.com/tensorflow/models/tree/master/research/deeplab

使用 TensorFlow DeepLab 进行语义分割

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Paper: https://arxiv.org/abs/1802.02611

Blog: https://research.googleblog.com/2018/03/semantic-image-segmentation-with.html

Code: https://github.com/tensorflow/models/tree/master/research/deeplab

使用TensorFlow Android Inference Interface在Android上进行图像物体检测

不支持Camera2 API的手机也可以物体检测：https://github.com/lijiancheng0614/android-TFDetect