The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its negative logarithm, we can get the loss formulation as follows:
$$ L_{t}\left(\mathcal{V}_{p}, \mathcal{V}_{n}\right)=-\frac{1}{M N} \sum_{i}^{M} \sum_{j}^{N} \log \operatorname{prob}\left(v p_{i}, v n_{j}\right) $$
where the balance weight $1/MN$ is used to keep the loss with the same scale for different number of instance sets.
Source: Triplet Loss in Siamese Network for Object TrackingPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Retrieval | 76 | 9.56% |
Metric Learning | 73 | 9.18% |
Person Re-Identification | 44 | 5.53% |
Image Retrieval | 32 | 4.03% |
Face Recognition | 21 | 2.64% |
General Classification | 21 | 2.64% |
Clustering | 18 | 2.26% |
Image Classification | 17 | 2.14% |
Few-Shot Learning | 16 | 2.01% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |