Learn how to design, develop, deploy and iterate on production-grade ML applications.

LAVIS - A One-stop Library for Language-Vision Intelligence

Code release for NeRF (Neural Radiance Fields)

PyTorch code and models for the DINOv2 self-supervised learning method.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

A framework for data augmentation for 2D and 3D image classification and segmentation

Image Segmentation and Object Detection in Pytorch

Language-Driven Semantic Segmentation

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Medical image processing in Python

MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation

QuadTree Attention for Vision Transformers (ICLR2022)

A Simple U-net model for Retinal Blood Vessel Segmentation based on tensorflow2

Tutorial Materials for ICCV19

(CVPR 2021 Oral) LETR: Line Segment Detection Using Transformers without Edges

A deep learning framework for synthesizing novel views of objects and scenes

Uncertainty quantification using Bayesian neural networks in classification (MIDL 2018, CSDA)

Visualizing the attention of vision-language models

Lecture notes for CS132

An algorithm that handles large-scale aerial photo co-registration, based on SURF, RANSAC and PyTorch autograd.

Superpixel-based Graph Convolutional Network for Semantic Segmentation

This code is provided for reproducibility of results in the paper: Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?