Pagml: Precise Alignment Guided Metric Learning for Sketch-Based 3d Shape Retrieval

Sketch-based 3D shape retrieval has always been a hot research topic in the computer vision community. The main challenge is to alleviate the cross-modality discrepancies such that the retrieval accuracy can be improved. In this paper, we propose a novel Precise Alignment Guided Metric Learning (PAGML) method based on master-auxiliary cross-modality retrieval framework. An auxiliary learning network is developed to indirectly guide the master learning model to extract features of rich semantic information, so as to achieve a semantic alignment between the cross-modality data. Furthermore, considering that the unbalanced data distributions led to the poor uniformity in the common embedding space, a loss function dedicated for the imbalanced cross-modality data is designed to achieve a rigid alignment between sketches and 3D shapes of the same category by pulling their rich semantic representations to the rigid center of the category. As a result, a more precise alignment between the cross-modality embedding features of same category is approached gradually, which further alleviates the cross-modality discrepancies and improves the cross-modality retrieval accuracies. Extensive experiments on two public benchmark datasets demonstrate that the proposed PAGML surpasses the state-of-the-art methods in retrieval accuracy and has excellent generalization abilities to unseen classes.