An open source implementation of CLIP.
-
Updated
Jul 4, 2024 - Python
An open source implementation of CLIP.
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
incremental learning experiments
This code is a custom implementation of the Supervised Contrastive Learning paper (https://arxiv.org/abs/2004.11362).
Official implementation for "Image Quality Assessment using Contrastive Learning"
Contrastive Unlearning
CLIP Like model fine tuned for the SemEval-2023 Visual-WSD task
Writer independent offline signature verification using convolutional siamese networks
The implement for paper : "Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval"
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
[ECCV 2022 Oral] Official Pytorch implementation of CCPL and SCTNet
Medical Image Similarity Search Using a Siamese Network With a Contrastive Loss
Implementation of Cyclist Pressure Research Paper
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
PyTorch implementation of the InfoNCE loss for self-supervised learning.
[ICRA 2022] The official repository for "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition", In 2022 International Conference on Robotics and Automation (ICRA), pp. 2215-2221.
This repository contains code for the PhD thesis: "A Study of Self-training Variants for Semi-supervised Image Classification" and publications.
Re-implementation of Intriguing Properties of Contrastive Losses paper
A deep learning solution using Siamese networks to solve the problem of face verification for an NGO. This was part of a winning solution for a competition held by Mastek. Competition link -
4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022
Add a description, image, and links to the contrastive-loss topic page so that developers can more easily learn about it.
To associate your repository with the contrastive-loss topic, visit your repo's landing page and select "manage topics."