Abstract
Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at this https URL.
Abstract (translated)
近年来,无监督显著物体检测(USOD)因其无需标注的特点而受到越来越多的关注。然而,目前的方法主要关注特定任务,如RGB和RGB-D,而忽略了潜在的任务迁移可能性。在本文中,我们提出了一种通用的USOD框架,用于通用USOD任务。首先,我们提出了一种基于渐进式课程学习的不透明度蒸馏(PCL-SD)机制,从预训练的深度网络中提取 saliency 线索。这种机制从容易的样本开始,逐渐转移到困难的样本,以避免由困难样本引起的初始干扰。接下来,获得的 saliency 线索用于训练 saliency 检测器,并采用自校正伪标签优化(SPR)机制来提高伪标签的质量。最后,一种适配器调整方法被提出,以转移获得的 saliency 知识,利用共享知识在目标任务上实现卓越的传输性能。在五个代表性SOD任务上进行的大量实验证实了我们提出方法的有效性和可行性。代码和补充材料可在此链接下载:https://www.example.com/
URL
https://arxiv.org/abs/2404.14759