.png){kind=icon}
返回
Recognition-Oriented Image Compressive Sensing With Deep Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3142952.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A number of image compressive sensing (CS) algorithms were proposed in the past two decades, aiming at yielding recovered images with the best possible visual effect. However, it is quite difficult to further improve the image quality for human eyes. For example, in the low-rate sampling scenarios, CS algorithms always suffer degraded performance and can only recover less visually appealing images. We notice that what human beings concern with is the visual quality of an image, while machine users care much more about its latent metrics, such as recognition accuracy, rather than the subjective visual effect. Inspired by this point, we develop a machine recognition-oriented image CS with an adversarial learning strategy. Some adversarial models are investigated to make the recognition accuracy as an additional optimization goal of the CS reconstruction network. Through end-to-end training, CS reconstruction network automatically learns an image recognition pattern, and produce recovered images owning extra recognition metric, which makes them become more suited for machine users. Experimental results indicate that the images recovered with the proposed adversarial learning strategy can be recognized with significantly higher accuracy compared to that with the existing CS algorithms.
Keyword:
Adversarial sample
compressive sensing
deep neural network
image recovery
machine recognition
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
Risk factors for intra-operative complications during phacoemulsification performed by residents
.png){kind=icon}
PREAI
分享收藏分享收藏
查看更多内容