IEEE Trans Pattern Anal Mach Intell. 2020 Aug;42(8):1913-1927. doi: 10.1109/TPAMI.2019.2905607. Epub 2019 Mar 18.
Previous research in visual saliency has been focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. In this work, we propose to employ the former model type to identify salient objects. We build a novel Attentive Saliency Network (ASNet) 1.Available at: https://github.com/wenguanwang/ASNet. that learns to detect salient objects from fixations. The fixation map, derived at the upper network layers, mimics human visual attention mechanisms and captures a high-level understanding of the scene from a global view. Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner. ASNet is based on a hierarchy of convLSTMs that offers an efficient recurrent mechanism to sequentially refine the saliency features over multiple steps. Several loss functions, derived from existing saliency evaluation metrics, are incorporated to further boost the performance. Extensive experiments on several challenging datasets show that our ASNet outperforms existing methods and is capable of generating accurate segmentation maps with the help of the computed fixation prior. Our work offers a deeper insight into the mechanisms of attention and narrows the gap between salient object detection and fixation prediction.
先前的视觉显著性研究主要集中在两种主要类型的模型上，即注视预测和显著目标检测。然而，这两者之间的关系还没有得到充分的探索。在这项工作中，我们建议使用前一种模型类型来识别显著目标。我们构建了一个新颖的注意显著性网络（ASNet）1.可在：https://github.com/wenguanwang/ASNet。它从注视中学习检测显著目标。在网络上层导出的注视图模仿了人类视觉注意机制，并从全局视图中捕获了对场景的高层理解。然后，将显著目标检测视为细粒度的对象级显著分割，并在注视图的指导下自上而下逐步优化。ASNet 基于层次结构的 convLSTM，提供了一种有效的递归机制，可以在多个步骤中逐步细化显著性特征。我们还结合了几种来自现有显著性评估指标的损失函数，以进一步提高性能。在几个具有挑战性的数据集上进行的广泛实验表明，我们的 ASNet 优于现有方法，并能够在计算出的注视先验的帮助下生成准确的分割图。我们的工作深入探讨了注意力的机制，并缩小了显著目标检测和注视预测之间的差距。
