All-in-One: Text Embedding, Retrieval, Reranking and RAG
-
Updated
Jul 12, 2024 - Python
All-in-One: Text Embedding, Retrieval, Reranking and RAG
Contrastive representation learning with PyTorch
Experiments of different pretext task on semantic segmentation and future frame prediction
Deep Learning - one shot learning for speaker recognition using Filter Banks
Self-training variants using PyTorch
This repository contains code for pretraining Wide Residual Network (WRN) using ImageNet
AsthmaSCELNet: A Lightweight Supervised Contrastive Embedding Learning Framework For Asthma Classification Using Lung Sounds
A tool to collect triplet queries
Self-supervised learning to boost time series classification models using a triplet loss mechanism.
Qualify-As-You-Go Sensor Fusion, Process Zone Signatures and Deep Contrastive Learning for Multi-Material Composition Monitoring in LPBF Process
Remaining Useful Life estimation and sensor data generation by VAE and diffusion model on C-MAPSS dataset.
his repository contains an implementation for eliminating backdoor triggers embedded in images, particularly addressing poison label attacks such as Trojan, BadNets, and Blend.
PyTorch implementation of unsupervised causal CNN encoder with triplet loss for time series representation learning.
Learning semantic embeddings from OSM data: A Pytorch implementation of the loc2vec general method outlined in: https://sentiance.com/loc2vec-learning-location-embeddings-w-triplet-loss-networks.
🎯 Task-oriented embedding tuning for BERT, CLIP, etc.
Resolving semantic confusions for improved zero-shot detection (BMVC 2022)
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"
The project implements Siamese Network with Triplet Loss in Keras to learn meaningful image representations in a lower-dimensional space. By training on the MNIST dataset, it creates a powerful architecture and implements Triplet Loss function. The resulting model enables applications like image search, recommendation systems, and image clustering.
Neural network for creating distortion while keeping embeddings as close as possible
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."