Loss Functions

Edit

General • 39 methods

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

Add a Method

Method	Year	Papers
Focal Loss Focal Loss for Dense Object Detection	2017	406
Cycle Consistency Loss Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks	2017	386
Triplet Loss Triplet Loss in Siamese Network for Object Tracking	2018	375
GAN Least Squares Loss Least Squares Generative Adversarial Networks	2016	364
InfoNCE Representation Learning with Contrastive Predictive Coding	2018	340
NT-Xent Improved Deep Metric Learning with Multi-class N-pair Loss Objective	2016	209
FLIP FLIP: A Difference Evaluator for Alternating Images	2020	171
GAN Hinge Loss Geometric GAN	2017	164
Dice Loss Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations	2017	90
ArcFace ArcFace: Additive Angular Margin Loss for Deep Face Recognition	2018	82
Huber loss	2000	66
Supervised Contrastive Loss Supervised Contrastive Learning	2020	61
WGAN-GP Loss Improved Training of Wasserstein GANs	2017	57
Adaptive Loss A General and Adaptive Robust Loss Function	2017	53
Early exiting BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks	2017	52
CTC Loss	2000	42
VGG Loss Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network	2016	34
uPIT Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation	2016	7
Balanced L1 Loss Libra R-CNN: Towards Balanced Learning for Object Detection	2019	6
Lovasz-Softmax	2000	5
Varifocal Loss VarifocalNet: An IoU-aware Dense Object Detector	2020	5
ElasticFace ElasticFace: Elastic Margin Loss for Deep Face Recognition	2021	5
HAPPIER Hierarchical Average Precision Training for Pertinent Image Retrieval	2022	4
Generalized Focal Loss Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection	2020	3
Rank-based Loss Rank-based loss for learning hierarchical representations	2021	3
Dynamic SmoothL1 Loss Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training	2020	2
Seesaw Loss Seesaw Loss for Long-Tailed Instance Segmentation	2020	2
ProxyAnchorLoss Proxy Anchor Loss for Deep Metric Learning	2020	2
Multi Loss ( BCE Loss + Focal Loss ) + Dice Loss HistoSeg : Quick attention with multi-loss function for multi-structure segmentation in digital histology images	2022	2
Self-Adjusting Smooth L1 Loss RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free	2019	1
DSAM loss DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio	2020	1
Triplet Entropy Loss Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems	2020	1
GHM-C Gradient Harmonized Single-stage Detector	2018	1
GHM-R Gradient Harmonized Single-stage Detector	2018	1
Metrix It Takes Two to Tango: Mixup for Deep Metric Learning	2021	1
PIoU Loss PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments	2020	1
Dual Softmax Loss Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss	2021	1
UFLoss High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss	2021	1
OA-Loss Object-Aware Domain Generalization for Object Detection	2023	1

Loss Functions Edit

Methods Add a Method

Loss Functions

Edit

Methods

Add a Method