frank-xwang

InstanceDiffusion

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

RIDE-LongTailRecognition

[ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."

CLD-UnsupervisedLearning

[CVPR 2021] Code release for "Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination."

debiased-pseudo-labeling

[CVPR 2022] Pytorch implementation for “Debiased Learning from Naturally Imbalanced Pseudo-Labels”

towards-universal-object-detection

[CVPR 2019] Pytorch implementation for "Towards Universal Object Detection by Domain Attention."

TBC-TiedBlockConvolution

[AAAI 2021] Pytorch implementation for "Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters."

VAI-ReinforcementLearning

[CVPR 2021] Pytorch implementation for "Unsupervised Visual Attention and Invariance for Reinforcement Learning."

ComfyUI-InstanceDiffusion

CutLER

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

assets

CLIP

Contrastive Language-Image Pretraining

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

FeatureTransfer

[CVPR 2018 Oral] Caffe implementation for "Feature Space Transfer for Data Augmentation."

darrellgroup.github.io

Website for Trevor Darrell's group at Berkeley

Detic

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

exponential-moving-average-normalization

PyTorch implementation of EMAN for self-supervised and semi-supervised learning: https://arxiv.org/abs/2101.08482

HIPIE

LaViLa

Code release for "Learning Video Representations from Large Language Models"

MarioNette

Code for MarioNette: Self-Supervised Sprite Learning, in NeurIPS 2021

Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

pycls

Codebase for Image Classification Research, written in PyTorch.

RIDE-Swin-LongTailRecognition

U2Seg

UniDet

Object detection on multiple datasets with an automatically learned unified label space.

VideoAutoencoder

Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoencoder/

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch