论文标题
FenceMask：预提取图像功能的数据增强方法
FenceMask: A Data Augmentation Approach for Pre-extracted Image Features
论文作者
论文摘要
我们提出了一种名为“ FenceMask”的新型数据增强方法，该方法在各种计算机视觉任务中表现出出色的性能。它基于“对象遮挡的模拟”策略，旨在实现对象遮挡和输入数据信息保留之间的平衡。通过增强闭塞块的稀疏性和规律性，我们的增强方法克服了小物体增强的难度，并显着改善了对基准的性能。足够的实验证明我们方法的性能比其他模拟对象遮挡方法更好。我们在CIFAR10，CIFAR100和IMAGENET数据集上进行了测试，以进行粗粒分类，可可2017和Vistrone数据集，用于检测，牛津花，玉米片叶和斯坦福犬数据集用于细粒度的视觉分类。我们的方法在细粒度的视觉分类任务和Visdrone数据集上取得了重大的性能提高。
We propose a novel data augmentation method named 'FenceMask' that exhibits outstanding performance in various computer vision tasks. It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between object occlusion and information retention of the input data. By enhancing the sparsity and regularity of the occlusion block, our augmentation method overcome the difficulty of small object augmentation and notably improve performance over baselines. Sufficient experiments prove the performance of our method is better than other simulate object occlusion approaches. We tested it on CIFAR10, CIFAR100 and ImageNet datasets for Coarse-grained classification, COCO2017 and VisDrone datasets for detection, Oxford Flowers, Cornel Leaf and Stanford Dogs datasets for Fine-Grained Visual Categorization. Our method achieved significant performance improvement on Fine-Grained Visual Categorization task and VisDrone dataset.
