Basic conception of loss function, dimension reduction, transfer learning, image classification.
-
Updated
Nov 24, 2022 - Jupyter Notebook
Basic conception of loss function, dimension reduction, transfer learning, image classification.
This is the ROS2 package including the tools for Soft Somatosensitive Sensor (SSS).
Demostrates a triplet loss to compute relationship between three image when one is similar to another and different from the third.
Facenet--Triplet loss for image embedding using Cifar100 dataset
Create a Convolutional Neural Network using TensorFlow.
Use Trax Siamese deep Neural LSTM Network to predict pair of similar question (duplicates)
Qualify-As-You-Go Sensor Fusion, Process Zone Signatures and Deep Contrastive Learning for Multi-Material Composition Monitoring in LPBF Process
Satellite Image Retrieval with Triplet Loss
Classification and Pose estimation using CNN, Quaternion Similarity and Triplet Loss
Perform Face Recognition with FaceNet on Avengers.
Using SigComp'11 dataset for signature verification (With Siamese network and triplet loss)
Self-training variants using PyTorch
Pytorch Implementation of the Paper A UNIFIED VIEW OF DEEP METRIC LEARNING VIA GRADIENT ANALYSIS
COVID-19 Question Dataset from the paper "What Are People Asking About COVID-19? A Question Classification Dataset"
Implementation of the following papers: Rádli, Richárd, Zsolt Vörösházi, and László Czúni. "Multi-Stream Pill Recognition with Attention." "Pill Metrics Learning with Multihead Attention" and "Word and Image Embeddings in Pill Recognition"
This works is an analysis of the feature space and comparison of the discriminative capability of features obtained from Autoencoders .In Deep learning literature these problems statements are called representation learning and through this work MNIST feature space and it's intricacies are visualized .
Spring 2022 Bioimage Informatics (Self-Study ) project using triplet loss and hard negative mining
Add a description, image, and links to the triplet-loss topic page so that developers can more easily learn about it.
To associate your repository with the triplet-loss topic, visit your repo's landing page and select "manage topics."