Loss Functions
Loss Functions are used to frame the problem to be optimized within deep learning. Below you will find a continuously updating list of (specialized) loss functions for neutral networks.
| METHOD | YEAR | PAPERS | |
|---|---|---|---|
Cycle Consistency Loss
|
2017 | 154 | |
GAN Least Squares Loss
|
2016 | 148 | |
Focal Loss
|
2017 | 139 | |
GAN Hinge Loss
|
2017 | 46 | |
InfoNCE
|
2018 | 31 | |
WGAN-GP Loss
|
2017 | 19 | |
VGG Loss
|
2016 | 18 | |
CTC Loss
|
2000 | 17 | |
ArcFace
|
2018 | 15 | |
NT-Xent
|
2016 | 5 | |
Lovasz-Softmax
|
2018 | 3 | |
Balanced L1 Loss
|
2019 | 2 | |
Supervised Contrastive Loss
|
2020 | 1 | |
Dynamic SmoothL1 Loss
|
2020 | 1 | |
Self-Adjusting Smooth L1 Loss
|
2019 | 1 |