Wisconsin AI and Vision Lab (WAIV)

yolact_edge

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

MixNMatch

Pytorch implementation of MixNMatch

few-shot-gan-adaptation

[CVPR '21] Official repository for Few-shot Image Generation via Cross-domain Correspondence

ViP-LLaVA

[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

UniversalFakeDetect

MaskPoint

[ECCV 2022] Masked Discrimination for Self-Supervised Learning on Point Clouds

visii

👀 Visual Instruction Inversion: Image Editing via Visual Prompting (NeurIPS 2023)

edit-one-for-all

✏️ Edit One for All: Interactive Batch Image Editing (CVPR 2024)

YoLLaVA

🌋👵🏻 Yo'LLaVA: Your Personalized Language and Vision Assistant

RISE

Domain Generalization through Distilling CLIP with Language Guidance

elastic-infogan

Official PyTorch implementation of Elastic-InfoGAN [NeurIPS 2020]

3detr_MaskPoint

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

W2D

The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

INPL

yolact

A simple, fully convolutional model for real-time instance segmentation.

GLIGEN

Open-Set Grounded Text-to-Image Generation

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"