Learning Saliency From Single Noisy Labelling: A Robust Model Fitting Perspective

Jing Zhang, Yuchao Dai, Tong Zhang, Mehrtash Harandi, Nick Barnes, Richard Hartley

Abstract

The advances made in predicting visual saliency using deep neural networks come at the expense of collecting large-scale annotated data. However, pixel-wise annotation is labor-intensive and overwhelming. In this paper, we propose to learn saliency prediction from a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single noisy labelling</i> , which is easy to obtain (e.g., from imperfect human annotation or from unsupervised saliency prediction methods). With this goal, we address a natural question: Can we learn saliency prediction while identifying clean labels in a unified framework? To answer this question, we call on the theory of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">robust model fitting</i> and formulate deep saliency prediction from a single noisy labelling as robust network learning and exploit model consistency across iterations to identify inliers and outliers (i.e., noisy labels). Extensive experiments on different benchmark datasets demonstrate the superiority of our proposed framework, which can learn comparable saliency prediction with state-of-the-art fully supervised saliency methods. Furthermore, we show that simply by treating ground truth annotations as noisy labelling, our framework achieves tangible improvements over state-of-the-art methods.
BibTeX
@article{zhang2021learning,
  author = {Jing Zhang and Yuchao Dai and Tong Zhang and Mehrtash Harandi and Nick Barnes and Richard Hartley},
  title = {{Learning Saliency From Single Noisy Labelling: A Robust Model Fitting Perspective}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2021},
  doi = {10.1109/tpami.2020.3046486},
}

Loading related content...

Figure