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

2023/02/09 by Khatib, Salwa Al, Boudjoghra, Mohamed El Amine, Hassan, Jameel
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2302.04800

Abstract

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.

Related

• Fine-Grained Object Classification via Self-Supervised Pose Alignment
• Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition
• Unsupervised Part Discovery via Dual Representation Alignment
• Alignment Based Matching Networks for One-Shot Classification and Open-Set Recognition
• Unsupervised Part Discovery via Feature Alignment