For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.
翻译:对于视觉物体识别任务,光化变异可能造成物体外观的明显变化,从而混淆基于深层神经网络的识别模型。 特别是对于某些罕见的光化条件,收集足够的培训样本可能耗时费钱。 为了解决这个问题,我们在本文件中提议建立一个名为隔离-光化网络(Sill-Net)的新型神经网络结构。 锡尔- 网络学会将光化特征与图像区分开来,然后在培训过程中,我们用地物空间中这些分离的光化特征来增加培训样本。 实验结果表明,我们的方法超越了几个物体分类基准中目前最先进的方法。