arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04800cs.CV
收藏

关注细节:通过自关注进行姿势对齐以实现细粒度对象分类

Drawing Attention to Detail: Pose Alignment through Self-Attention for Fine-Grained Object Classification

MBZUAI(穆罕默德·本·扎耶德人工智能大学)

Salwa Al Khatib, Mohamed El Amine Boudjoghra, Jameel Hassan

摘要:

开放世界中的类内差异导致分类任务面临各种挑战。为了克服这些挑战,引入了细粒度分类,并提出了许多方法。一些依赖于定位和使用图像中可区分的局部部分,以实现对视点变化、类内差异和局部部分变形的不变性。我们的方法,这是P2P-Net的启发,提供了一个端到端的可训练的基于注意力的部件对齐模块,在那里我们取代了图形匹配组件中使用的自我注意力机制。注意力模块能够在导致全局损失之前,在相互注意的同时学习部件的最佳布置。

英文摘要:

Intra-class variations in the open world lead to various challenges in classification tasks. To overcome these challenges, fine-grained classification was introduced, and many approaches were proposed. Some rely on locating and using distinguishable local parts within images to achieve invariance to viewpoint changes, intra-class differences, and local part deformations. Our approach, which is inspired by P2P-Net, offers an end-to-end trainable attention-based parts alignment module, where we replace the graph-matching component used in it with a self-attention mechanism. The attention module is able to learn the optimal arrangement of parts while attending to each other, before contributing to the global loss.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑