Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

Add code
Apr 05, 2020
Benyamin Ghojogh, Milad Sikaroudi, Sobhan Shafiei, H. R. Tizhoosh, Fakhri Karray, Mark Crowley

Figure 1 for Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
Figure 2 for Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
Figure 3 for Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
Figure 4 for Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Siamese neural network is a very powerful architecture for both feature extraction and metric learning. It usually consists of several networks that share weights. The Siamese concept is topology-agnostic and can use any neural network as its backbone. The two most popular loss functions for training these networks are the triplet and contrastive loss functions. In this paper, we propose two novel loss functions, named Fisher Discriminant Triplet (FDT) and Fisher Discriminant Contrastive (FDC). The former uses anchor-neighbor-distant triplets while the latter utilizes pairs of anchor-neighbor and anchor-distant samples. The FDT and FDC loss functions are designed based on the statistical formulation of the Fisher Discriminant Analysis (FDA), which is a linear subspace learning method. Our experiments on the MNIST and two challenging and publicly available histopathology datasets show the effectiveness of the proposed loss functions.

* Accepted (to appear) in International Joint Conference on Neural Networks (IJCNN) 2020, IEEE, in IEEE World Congress on Computational Intelligence (WCCI) 2020  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon