Deep Metric Learning

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.

[CVPR 2024] Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

A dependency free library of standardized optimization test functions written in pure Python.

Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.

Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction

Angular triplet center loss implementation in Pytorch.

Directional Distance Field for Modeling the Difference between 3D Point Clouds

Tensorflow Implementation of Focal Frequency Loss for Image Reconstruction and Synthesis [ICCV 2021]

A simple 3-layer fully connected network performing the density ratio estimation using the loss for log-likelihood ratio estimation (LLLR).

Official PyTorch implementation for "PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks"

Adversarial Focal Loss: Asking Your Discriminator for Hard Examples.

MultiScale Signature feature learning Network for offline handwritten signature verification

Piecewise linear approximations for the static-dynamic uncertainty strategy in stochastic lot-sizing

Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation

[TPAMI 2023] PyTorch code for Sparse Label Smoothing Regularization presented in "Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning". Paper Link: https://arxiv.org/abs/2209.08907

Tensor-Network Machine Learning with Matrix Product States, trained via a surrogate (projective) loss instead of standard negative log-likelihood

A neat, lightweight and single neuron perceptron written in C++ from scratch without any external library, trained using the perceptron trick and loss function

An HR predictive analytics tool for forecasting the likely range of a worker’s future job performance using multiple ANNs with custom loss functions.

Bahdanau Attention Mechanism | Tensorflow Custom Layers/Model/Loss Function/Metrics | LSTM | Encoder | Decoder | Cross-Attention | Language Translation | Bleu Score | Dropout

Inverse Supervised Learning

OpenLoss: This repository discloses cost functions designed for open-set classification tasks, namely, Entropic Open-set, ObjectoSphere and Maximal-Entropy Loss.

Generating a TensorFlow model that predicts values in a sinewave

📄 Official implementation regarding the paper "Programmatically Evolving Losses in Machine Learning".

No description provided.

Alternative loss function of binary cross entropy and focal loss

Projeto que utiliza a base de dados Iris para calcular a acurácia e a função de perda de um modelo de aprendizado de máquina. Focado em análise de desempenho e avaliação de modelos.