中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组


News / Events

VIPL's paper on robust SVP prediction is accepted by IEEE TPAMI

Date of publication:2020-12-25      Number of clicks: 0

Recently, VIPL's paper on robust SVP prediction was accepted by IEEE TPAMI. IEEE PAMI, i.e, IEEE Transactions on Pattern Analysis and Machine Intelligence is a CCF-ranked-A top-tier Artificial Intelligence journal with a high IF score as 17.86. Below is a brief introduction of this work.

 

Qianqian Xu, Zhiyong Yang, Yangbangyan JiangXiaochun CaoYuan Yao Qingming Huang*. “Not All Samples are Trustworthy: Towards Deep Robust SVP Prediction”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020. (Accepted)

 

In this paper, we study the problem of estimating subjective visual properties (SVP) for images, which is an emerging task in Computer Vision. Generally speaking, collecting SVP datasets involves a crowdsourcing process where annotations are obtained from a wide range of online users. Since the process is done without quality control, SVP datasets are known to suffer from noise. This leads to the issue that not all samples are trustworthy. Facing this problem, we need to develop robust models for learning SVP from noisy crowdsourced annotations. In this paper, we construct two general robust learning frameworks for this application. Specifically, in the first framework, we propose a probabilistic framework to explicitly model the sparse unreliable patterns that exist in the dataset. It is noteworthy that we then provide an alternative framework that could reformulate the sparse unreliable patterns as a “contraction” operation over the original loss function. The latter framework leverages not only efficient end-to-end training but also rigorous theoretical analyses. To apply these frameworks, we further provide two models as implementations of the frameworks, where the sparse noise parameters could be interpreted with the HodgeRank theory. Finally, extensive theoretical and empirical studies show the effectiveness of our proposed framework.

 



中科院计算所视觉信息处理与学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号-1 京公网安备1101080060