论文标题
快速：视觉显着性预测的计算高效网络
FastSal: a Computationally Efficient Network for Visual Saliency Prediction
论文作者
论文摘要
本文重点介绍了视觉显着性预测的问题，预测了在有限的计算预算下，图像的区域往往吸引人类视觉关注。我们修改和测试了各种近期有效的卷积神经网络体系结构，例如有效网络和MobilenetV2，并将它们与现有的最新显着性模型（如Salgan和Deepgaze II）进行了比较，包括AUC和NSS（例如AUC和NSS），以及计算复杂性和模型大小。我们发现Mobilenetv2是视觉显着性模型的绝佳骨干，即使没有复杂的解码器也可以有效。我们还表明，从更昂贵的模型（例如Deepgaze II）中的知识转移可以通过伪标记的数据集来实现，并且这种方法具有许多最先进的算法，而计算成本和模型尺寸的一小部分为您提供了PAR的结果。源代码可从https://github.com/feiyanhu/fastsal获得。
This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional neural network architectures like EfficientNet and MobileNetV2 and compare them with existing state-of-the-art saliency models such as SalGAN and DeepGaze II both in terms of standard accuracy metrics like AUC and NSS, and in terms of the computational complexity and model size. We find that MobileNetV2 makes an excellent backbone for a visual saliency model and can be effective even without a complex decoder. We also show that knowledge transfer from a more computationally expensive model like DeepGaze II can be achieved via pseudo-labelling an unlabelled dataset, and that this approach gives result on-par with many state-of-the-art algorithms with a fraction of the computational cost and model size. Source code is available at https://github.com/feiyanhu/FastSal.
