Multi-Level Metric Learning Network for Fine-Grained Classification

Multi-Level Metric Learning Network for Fine-Grained Classification

Blog Article

The application of fine-grained image classification can be problematic due to subtle differences between classes.The existing global feature-based methods have worse accuracies than regional feature-based methods, because regional feature-based methods focus on the determination of differentiated features within local Horse Leg Bandages regions.To learn more discriminative global features, in this paper, we proposed the use of L2 normalization to tackle a neglected conflict between the widely used metric loss (triplet loss) and classification loss (softmax loss) in global feature-based methods.Furthermore, a multi-level metric learning network (MMLN) is proposed for fine-grained image classification based on global features.In the MMLN, multi-level metric learning objectives and classification objectives are present at multiple high-level layers.

The multi-level metric learning objectives work together to supervise the network in order to learn highly discriminative features.In addition, a new probability aggregation strategy (PAS) is proposed to produce a fused prediction by combining the multi-level predictive probabilities.Experiments were conducted on three standard fine-grained #4 MEDIUM BROWN classification datasets (CUB-200-2011, Stanford Cars, and FGVC-Aircraft).Results demonstrated that our MMLN achieved accuracies of 88.0%, 94.

6% and 92.4% respectively and outperformed state-of-the-art methods, substantially improving fine-grained classification tasks.Besides, gradient-weighted class activation mapping (Grad-CAM) shows that the MMLN is able to pay more attention to the discriminative local regions due to the application of multi-level metric learning.