Recent advancements in deep convolutional neural networks have significantly improved the performance of saliency prediction. However, the manual configuration of the neural network architectures requires domain knowledge expertise and can still be time-consuming and error-prone. To solve this, we propose a new Neural Architecture Search (NAS) framework for saliency prediction with two contributions. Firstly, a supernet for saliency prediction is built with a weight-sharing network containing all candidate architectures, by integrating a dynamic convolution into the encoder-decoder in the supernet, termed SalNAS. Secondly, despite the fact that SalNAS is highly efficient (20.98 million parameters), it can suffer from the lack of generalization. To solve this, we propose a self-knowledge distillation approach, termed Self-KD, that trains the student SalNAS with the weighted average information between the ground truth and the prediction from the teacher model. The teacher model, while sharing the same architecture, contains the best-performing weights chosen by cross-validation. Self-KD can generalize well without the need to compute the gradient in the teacher model, enabling an efficient training system. By utilizing Self-KD, SalNAS outperforms other state-of-the-art saliency prediction models in most evaluation rubrics across seven benchmark datasets while being a lightweight model. The code will be available at https://github.com/chakkritte/SalNAS

翻译：近年来，深度卷积神经网络的进展显著提升了显著性预测的性能。然而，神经网络架构的手动配置需要领域专业知识，且仍可能耗时且容易出错。为解决此问题，我们提出了一种用于显著性预测的新型神经架构搜索框架，该框架包含两项贡献。首先，通过将动态卷积集成到超网的编码器-解码器中，构建了一个包含所有候选架构的权重共享网络作为显著性预测的超网，称为SalNAS。其次，尽管SalNAS具有高效性（参数量为20.98百万），但仍可能面临泛化能力不足的问题。为此，我们提出了一种自知识蒸馏方法，称为Self-KD，该方法利用真实标签与教师模型预测值之间的加权平均信息来训练学生模型SalNAS。教师模型与学生模型共享相同架构，但其权重通过交叉验证选择为性能最优的权重。Self-KD能够在无需计算教师模型梯度的情况下实现良好泛化，从而构建了一个高效的训练系统。通过采用Self-KD，SalNAS在七个基准数据集上的大多数评估指标中均优于其他最先进的显著性预测模型，同时保持了轻量级特性。代码将在https://github.com/chakkritte/SalNAS 公开。