Official code repo for Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images (The 3rd VDU Workshop @ CVPR 2024).

The open-source tool for building high-quality datasets and computer vision models

A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems

utilities for decoding deep representations (like sentence embeddings) back to text

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

The Conceptual Coverage Across Languages Benchmark for Text-to-Image Models

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

The Official Repository for CVPR2023 Paper "NICO++: Towards Better Benchmarking for Domain Generalization".

Open-Set Grounded Text-to-Image Generation

ReCo: Region-Controlled Text-to-Image Generation, CVPR 2023

[Neurips 2023] T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"

Debug PyTorch code using PySnooper

Semi-supervised Domain Adaptation via Minimax Entropy

Official repo for consistency models.

NLP tool for wide-range model reliability evaluations

Inference code for Llama models

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

🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

Whisper based Japanese subtitle generator

Locally run an Instruction-Tuned Chat-Style LLM

My best practice of training large dataset using PyTorch.

Easily create large video dataset from video urls

PyTorch code for “TVLT: Textless Vision-Language Transformer” (NeurIPS 2022 Oral)

A fast approach for translating a series of text prompts into a video. The 2022 NeurIPS Workshop on Machine Learning for Creativity and Design