contrastive-language-image-pretraining

🛰️ Official repository of paper "RemoteCLIP: A Vision Language Foundation Model for Remote Sensing" (IEEE TGRS)

[WACV 2026] An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.

[ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining

RadCLIP is a foundation model for radiologic imaging that leverages a Vision–Language Pre-training (VLP) framework to align 2D/3D radiologic images with their textual descriptions, improving diagnostic accuracy and efficiency in clinical workflows.

Use CLIP to create matching texts + embeddings for given images; useful for XAI, adversarial training

This application fine-tunes the CLIP model on the Flickr8k dataset to align image and text embeddings for image-caption matching. The goal is to enhance multimodal understanding and retrieval performance using a custom captioning dataset.

Theory, Experiments, and Dataset for our newly proposed Deep Learning method for Heuristics-driven Cycle Consistency and Semantics Aware Self-Supervised Framework for Unpaired LDR ↔ HDR Image Translation

Simple data and training pipeline for class-incremental method 😄

CLIP-interrogator InvokeAI node

Visual and Vision-Language Representation Pre-Training with Contrastive Learning

Attempts to improve CLIP via different optimizers and loss functions

PLoP applied to CLIP

AI Tagger that indexes existing images, and uses index to tag untagged images.

A multi-model inference workflow that uses YOLOv8 to detect vessel types in optical satellite images and uses CLIP for zero-shot prediction of cargo status.

University project based on implementing a Test Time Adaptation (TTA) solution for image classifiers. University of Trento (Italy)