Methods › General › Loss Functions

Loss Functions

43 methods 3,015 papers tagged archive 2025-07-28

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.

Methods

All 43 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

Focal Loss – 461
Cycle Consistency Loss – 448
Triplet Loss – 424
GAN Least Squares Loss – 421
InfoNCE – 418
NT-Xent Normalized Temperature-scaled Cross Entropy Loss – 251
FLIP – 237
GAN Hinge Loss – 167
Dice Loss – 108
ArcFace Additive Angular Margin Loss – 94
Huber loss – 77
Supervised Contrastive Loss – 76
Adaptive Loss Adaptive Robust Loss – 73
Early exiting Early exiting using confidence measures – 66
WGAN-GP Loss – 65
CTC Loss Connectionist Temporal Classification Loss – 47
VGG Loss – 37
Varifocal Loss – 8
Balanced L1 Loss – 7
uPIT utterance level permutation invariant training – 7
ElasticFace Elastic Margin Loss for Deep Face Recognition – 5
HAPPIER Hierarchical Average Precision training for Pertinent ImagE Retrieval – 5
Lovasz-Softmax – 5
Generalized Focal Loss – 4
Nebula – 4
Rank-based Loss Rank-based loss – 4
Dynamic SmoothL1 Loss – 3
Seesaw Loss – 3
Multi Loss ( BCE Loss + Focal Loss ) + Dice Loss – 2
ProxyAnchorLoss Proxy Anchor Loss for Deep Metric Learning – 2
ZLPR Loss Zero-bounded Log-sum-exp & Pairwise Rank-based Loss – 2
DHEL Decoupled Hyperspherical Energy Loss – 1
DSAM loss Distance Shrinking with Angular Marginalizing Loss – 1
Dual Softmax Loss – 1
GHM-C Gradient Harmonizing Mechanism C – 1
GHM-R Gradient Harmonizing Mechanism R – 1
HBM Loss Hierarchy-aware Biased Bound Margin Loss – 1
Metrix Metric mixup – 1
OA-Loss Object-Aware Loss – 1
PIoU Loss – 1
Self-Adjusting Smooth L1 Loss – 1
Triplet Entropy Loss – 1
UFLoss Unsupervised Feature Loss – 1