CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Reference PyTorch implementation and models for DINOv3

FLAME head tracker for single image reconstruction and monocular video tracking. [Note: This tracker operates offline and is not intended for real-time applications.]

OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]

Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.

A PyTorch implementation of MedSegDiff, a diffusion probabilistic model designed for medical image segmentation.

A PyTorch implementation of various deep generative models, including Diffusion (DDPM), GAN, cGAN, and VAE.

Vision-Language Models Toolbox: Your all-in-one solution for multimodal research and experimentation

Advance information retrieval system that combines advanced indexing, machine learning, and personalized search to enhance academic research and document discovery.

A step-by-step implementation of a ResNet-18 model for image classification on the CIFAR-10 dataset

Fine-tuning a RoBERTa model for sentiment analysis on the IMDB movie reviews dataset using the Adapter method and PyTorch Transformers

BYOL (Bootstrap Your Own Latent), implemented from scratch in Pytorch

Analysis of Classical Machine Learning Algorithms for Anomaly Detection in Time Series Data

Evaluating CNN robustness against various adversarial attacks, including FGSM and PGD.

fine-tuned BERT and scikit-learn models for real-time classification of disaster-related tweets, using TensorFlow, Keras, and Transformers. .

PyTorch UNet model for semantic segmentation of urban scenes using the Cityscapes dataset

Repository with the VisionQAries Team's solution for the MEDIQA-MAGIC Task at ImageCLEF 2024.

Fine-tuning an encoder-decoder transformer (ViT-Base-Patch16-224-In21k and DistilGPT2) for image captioning on the COCO dataset

Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.