Triplet loss is a loss function for machine learning algorithms where a baseline input is compared to a positive input and a negative input. The distance from the baseline input to the positive input is minimized, and the distance from the baseline input to the negative input is maximized. By enforcing the order of distances, triplet loss models embed in the way that a pair of samples with same labels are smaller in distance than those with different labels. Unlike t-SNE which preserves embedding orders via probability distributions, triplet loss works directly on embedded distances. Therefore, in its common implementation, it needs soft margin treatment with a slack variable in its hinge loss-style formulation. It is often used for learning similarity for the purpose of learning embeddings, such as learning to rank, word embeddings, thought vectors, and metric learning.. Consider the task of training a neural network to recognize faces. A classifier trained to classify an instance would have to be retrained every time a new person is added to the face database. This can be avoided by posing the problem as a similarity learning problem instead of a classification problem. Here the network is trained to output a distance which is small if the imagebelongs to a known person and large if the image belongs to an unknown person. However, if we want to output the closest images to a given image, we would like to learn a ranking and not just a similarity. A triplet loss is used in this case. The loss function can be described using a Euclidean distance function This can then be used in a cost function, that is the sum of all losses, which can then be used for minimization of the posed optimization problem The indices are for individual input vectors given as a triplet. The triplet is formed by drawing an anchor input, a positive input that describes the same entity as the anchor entity, and a negative input that does not describe the same entity as the anchor entity. These inputs are then run through the network, and the outputs are used in the loss function.
Comparison and Extensions
In computer vision tasks such as re-identification, a prevailing belief has been that the triplet loss is inferior to using surrogate losses followed by separate metric learning steps. Alexander Hermans, Lucas Beyer, and Bastian Leibe showed that for models trained from scratch, as well as pretrained models, a special version of triplet loss doing end-to-end deep metric learning outperforms most other published methods as of 2017. Additionally, triplet loss has been extended to simultaneously maintain a series of distance orders by optimizing a continuous relevance degree with a chain of distance inequalities. This leads to the Ladder Loss, which has been demonstrated to offer performance enhancements of visual-semantic embedding in learning to rank tasks.
