Abstract
Edge detection, as a core component in a wide range of visionoriented tasks, is to identify object boundaries and prominent edges in natural images. An edge detector is desired to be both efficient and accurate for practical use. To achieve the goal, two key issues should be concerned: 1) How to liberate deep edge models from inefficient pre-trained backbones that are leveraged by most existing deep learning methods, for saving the computational cost and cutting the model size; and 2) How to mitigate the negative influence from noisy or even wrong labels in training data, which widely exist in edge detection due to the subjectivity and ambiguity of annotators, for the robustness and accuracy. In this paper, we attempt to simultaneously address the above problems via developing a collaborative learning based model, termed PEdger. The principle behind our PEdger is that, the information learned from different training moments and heterogeneous (recurrent and non recurrent in this work) architectures, can be assembled to explore robust knowledge against noisy annotations, even without the help of pre-training on extra data. Extensive ablation studies together with quantitative and qualitative experimental comparisons on the BSDS500 and NYUD datasets are conducted to verify the effectiveness of our design, and demonstrate its superiority over other competitors in terms of accuracy, speed, and model size. Codes can be found at this https URL.
Abstract (translated)
边缘检测作为视觉任务中的核心组件,旨在在自然图像中识别物体边界和突出的边缘。为了实现目标,需要关注两个关键问题:1) 如何从不同的训练时刻和异构(在本文中为持续和非持续)架构中解放深度边缘模型,以减少计算成本和减小模型大小,以节省计算资源和提高模型鲁棒性;2) 如何减轻训练数据中的噪声或甚至错误标签的负面影响,由于标注员的主观性和不确定性,这种现象在边缘检测中非常普遍,以增强性和准确性为目的。在本文中,我们试图通过开发一种协同学习基于模型的方法,称为PEdger,同时解决上述问题。我们的PEdger原则是,从不同的训练时刻和异构(在本文中为持续和非持续)架构中学习的信息可以组装起来,探索对抗噪声标注的稳健知识,即使没有额外的训练数据的帮助。进行了广泛的削减研究和对BSDS500和NYU-D数据集的定量和定性实验比较,以验证我们的设计的有效性,并证明在准确性、速度和模型大小方面优于其他竞争对手。代码可在本URL找到。
URL
https://arxiv.org/abs/2308.14084
