See Clearly in the Distance: Representation Learning GAN for Low Resolution Object Recognition
See Clearly in the Distance: Representation Learning GAN for Low Resolution Object Recognition
复制标题
DOI：
10.1109/access.2020.2978980
复制
发表时间：
2020-03
期刊：
影响因子：
3.9
通讯作者：
Yue Xi;Jiangbin Zheng;W. Jia;Xiangjian He;Hanhui Li;Zhuqiang Ren;K. Lam
中科院分区：
文献类型：
--
作者：
Yue Xi;Jiangbin Zheng;W. Jia;Xiangjian He;Hanhui Li;Zhuqiang Ren;K. Lam
由于物体区域内呈现的信息有限，识别极低分辨率的微小物体通常被认为是一项非常具有挑战性的任务，即使对人类视觉来说也是如此。近年来，处理低分辨率识别的尝试非常有限。现有的解决方案要么依赖于生成超分辨率图像，要么依赖于学习多尺度特征。然而，它们的性能改进变得非常有限，特别是当分辨率变得非常低时。在本文中，我们提出了一种表示学习生成对抗网络(RL-GAN)来生成针对识别进行优化的超级图像表示。我们的解决方案处理的是传统的视觉任务，即远距离目标识别。我们在具有挑战性的低分辨率目标识别任务中对我们的想法进行了评估。在公共数据集和我们新创建的更广泛的数据集上进行的实验结果表明，我们的RL-GAN算法是有效的，与基准解决方案相比，它显著地改善了分类结果，平均提高了10%-15%。
Identifying tiny objects with extremely low resolution is generally considered a very challenging task even for human vision, due to limited information presented inside the object areas. There have been very limited attempts in recent years to deal with low-resolution recognition. The existing solutions rely on either generating super-resolution images or learning multi-scale features. However, their performance improvement becomes very limited, especially when the resolution becomes very low. In this paper, we propose a Representation Learning Generative Adversarial Network (RL-GAN) to generate super image representation that is optimized for recognition. Our solution deals with the classical vision task of object recognition in the distance. We evaluate our idea on the challenging task of low-resolution object recognition. Comparison of experimental results conducted on public and our newly created WIDER-SHIP datasets demonstrate the effectiveness of our RL-GAN, which improves the classification results significantly, with 10–15% gain on average, compared with benchmark solutions.