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.
keras implementation of triplet-loss and triple-center-loss
PyTorch implementation of "Open-set Recognition of Unseen Macromolecules in Cellular Electron Cryo-Tomograms by Soft Large Margin Centralized Cosine Loss"
Hybrid Data Augmentation and Attention-based Dilated Convolutional-Recurrent Neural Networks for Speech Emotion Recognition
keras implementation of metric-based methods (center-loss, circle-loss, triplets...)
training model using center-loss for face recognition
One-shot face identification using deep learning
Based on https://github.com/Arsey/keras-transfer-learning-for-oxford102, but more things are done in the project. Especially for the triplet and center loss.
The final project of DLCV course (CommE 5052) on NTU
In this repository, we implement and review state of the art papers in the field of face recognition and face detection, and perform operations such as face verification and face identification with Deep models like Arcface, MTCNN, Facenet and so on.
Official companion repository for the paper "A Metric Learning Approach to Misogyny Categorization" at the 5th Workshop on Representation Learning for NLP, ACL 2020
Evaluating the effectiveness of using standalone center loss.
keras implementation of A Discriminative Feature Learning Approach for Deep Face Recognition based on MNIST
This repository contains the ipynb for a project on deep learning visual classification of food categories
Similarity Learning applied to Speaker Verification and Semantic Textual Similarity
PyTorch Implementation for the paper "DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors" (ECCVW'20).
This is an implementation of the Center Loss article (2016).
PyTorch Implementation for the paper "C3VQG: Category Consistent Cyclic Visual Question Generation" (ACM MM Asia'20).
Add a description, image, and links to the center-loss topic page so that developers can more easily learn about it.
To associate your repository with the center-loss topic, visit your repo's landing page and select "manage topics."