【摘要】 细粒度图像中物体的分割是具有挑战性的,因为这类图像一般具有很大的表观变化和混杂的背景。大多数已有的分割方法都不能以足够的准确率将细粒度图像中物体的细小部件分割出来。然而在细粒度识别任务中,这些细小的部件通常包含了对细粒度分类极为重要的语义信息。通过观察发现,细粒度物体通常在类间共享相同的部件种类,本文由此提出一种新颖的基于部件检测的细粒度图像分割方法。该方法明确地检测部件在图像中的位置,给出部件位置假设。然后通过不断地迭代更新部件假设和分割的输出假设,以获得更优的分割效果。实验表明本文方法能够很好地保留具有语音信息的部件,提高细粒度分类的准确率。更多还原

【Abstract】 It is challenging to segment fine-grained objects due to appearance variations and clutter of backgrounds. Most of existing segmentation methods hardly separate small parts of the instance from its background with sufficient accuracy. However,such small parts usually contain important semantic information,which is crucial in fine-grained categorization. Observing that fine-grained objects almost share the same configuration of parts,the paper presents a novel part-aware segmentation method,which explicitly detects semantic parts and preserves these parts during segmentation. The paper firstly designs a hybrid part localization method,which generates accurate part proposals with moderate computation. Then the paper iteratively updates the segmentation outputs and the part proposals,which obtains better foreground segmentation results. Experiments demonstrate the superiority of the proposed method,as compared to state-of-the-art segmentation approaches for fine-grained categorization.更多还原