Xinyu Huang's repositories
recognize-anything
Open-source and strong foundation image recognition models.
robust-loss-mlml
Code for paper: Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
IDEA-pytorch
Code for paper: IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training [ACM MM2022]
ActionCLIP
This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"
daily_fudan
一键平安复旦小脚本,自动化快速上报疫情
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Tag2Text & Stable Diffusion & BLIP & Whisper - Automatically Recognize, Detect, Segment and Generate Anything with Image, Text, and Speech Inputs
GroundingDINO
The official implementation of "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
object_detection_metrics
Object Detection Metrics
query2labels
Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.