arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1601.04153cs.CVcs.AIcs.LG
收藏

使用深度网络研究极低分辨率识别

Studying Very Low Resolution Recognition Using Deep Networks

Beckman Institute, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校贝克曼研究所)

Zhangyang Wang, Shiyu Chang, Yingzhen Yang, Ding Liu, Thomas S. Huang

摘要:

视觉识别研究通常假设感兴趣区域(ROI)具有足够的分辨率。这在实践中通常会被违反,这激发了我们探索极低分辨率识别(VLRR)问题。通常,VLRR问题中的ROI可能小于$16 \times 16$像素,并且即使由人类专家识别也具有挑战性。我们尝试使用深度学习方法来解决VLRR问题。利用主要在超分辨率,领域自适应和鲁棒回归的技术,我们制定了一个专用的深度学习方法,并演示了如何将这些技术逐步纳入。任何额外的复杂性,引入时,是完全合理的分析和仿真结果。最后得到的\textit{Robust Partially Coupled Networks}同时实现了特征增强和识别。它允许灵活地对抗LR-HR域不匹配,以及对离群值的鲁棒性。最后,所提出的模型的有效性进行了评估,在三个不同的VLRR任务,包括人脸识别,数字识别和字体识别,所有这些都获得了非常令人印象深刻的性能。

英文摘要:

Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to explore the Very Low Resolution Recognition (VLRR) problem. Typically, the ROI in a VLRR problem can be smaller than $16 \times 16$ pixels, and is challenging to be recognized even by human experts. We attempt to solve the VLRR problem using deep learning methods. Taking advantage of techniques primarily in super resolution, domain adaptation and robust regression, we formulate a dedicated deep learning method and demonstrate how these techniques are incorporated step by step. Any extra complexity, when introduced, is fully justified by both analysis and simulation results. The resulting \textit{Robust Partially Coupled Networks} achieves feature enhancement and recognition simultaneously. It allows for both the flexibility to combat the LR-HR domain mismatch, and the robustness to outliers. Finally, the effectiveness of the proposed models is evaluated on three different VLRR tasks, including face identification, digit recognition and font recognition, all of which obtain very impressive performances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑