Deep Learning-based Unsupervised Salient Object Detection (USOD) mainly relies on the noisy saliency pseudo labels that have been generated from traditional handcraft methods or pre-trained networks. To cope with the noisy labels problem, a class of methods focus on only easy samples with reliable labels but ignore valuable knowledge in hard samples. In this paper, we propose a novel USOD method to mine rich and accurate saliency knowledge from both easy and hard samples. First, we propose a Confidence-aware Saliency Distilling (CSD) strategy that scores samples conditioned on samples' confidences, which guides the model to distill saliency knowledge from easy samples to hard samples progressively. Second, we propose a Boundary-aware Texture Matching (BTM) strategy to refine the boundaries of noisy labels by matching the textures around the predicted boundary. Extensive experiments on RGB, RGB-D, RGB-T, and video SOD benchmarks prove that our method achieves state-of-the-art USOD performance.

翻译：基于深度学习的无监督显著性目标检测（USOD）主要依赖于从传统手工方法或预训练网络中生成的含噪显著性伪标签。为应对噪声标签问题，一类方法仅聚焦于带有可靠标签的简单样本，却忽略了困难样本中的有价值知识。本文提出一种新颖的USOD方法，旨在从简单样本和困难样本中同时挖掘丰富且准确的显著性知识。首先，我们提出一种置信度感知的显著性蒸馏（CSD）策略，该策略根据样本的置信度对样本进行评分，从而引导模型逐步从简单样本向困难样本蒸馏显著性知识。其次，我们提出一种边界感知的纹理匹配（BTM）策略，通过匹配预测边界周围的纹理来优化噪声标签的边界。在RGB、RGB-D、RGB-T以及视频SOD基准上进行的大量实验表明，我们的方法达到了最先进的USOD性能。