Multi-Scale Attention Constraint Network for Fine-Grained Visual Classification
Lists
Only you see this
Abstract
Capturing subtle yet discriminative features constitutes a great challenge in fine-grained visual classification due to the large intra-class and small inter-class variances. Main-stream works for this problem localize at attention mechanism and feature relationship learning. However, existing methods treat the features in isolation while neglecting the effect of attention-enhanced features on relationships between different network layers. In this paper, we propose a novel attention-based method by Multi-Scale Attention Constraint network composed of two important components: (1) a feature extractor with lightweight group-wise enhanced attention blocks that guides the generation of high representation features; and (2) a multi-scale regularizer that explores the relationships between different features. Extensive experiments show that our approach achieves state-of-the-art performance on standard benchmark datasets. Moreover, we introduce a new dataset, consisting of comprehensive surgical instrument categories based on three common surgeries, to support the classification and inventory work of surgical instruments.
BibTeX
@inproceedings{hou2021multi,
author = {Yaqing Hou and Wenkai Zhang and Dongsheng Zhou and Hongwei Ge and Qiang Zhang and Xiaopeng Wei},
title = {{Multi-Scale Attention Constraint Network for Fine-Grained Visual Classification}},
booktitle = {ICME},
year = {2021},
url = {https://openreview.net/forum?id=1scDIOCiXO},
}Loading related content...