Awj2021's repositories
ProMix
PyTorch Code for ProMix: Combating Label Noise via Maximizing Clean Sample Utility
unionnet
Replementation of unionnet "Deep Learning from Multiple Noisy Annotators as A Union"
classifier-free-diffusion-guidance-Pytorch
a simple unofficial implementation of classifier-free diffusion guidance
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
open_clip
An open source implementation of CLIP.
tiny-transformers
[ECCV 2022] Implementation of the paper "Locality Guidance for Improving Vision Transformers on Tiny Datasets"
ControlNet
Let us control diffusion models!
MKT
Official implementation of "Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer".
IP-Adapter
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
TestProjects
Mainly including some test files, like jupyter notebooks
VMamba
VMamba: Visual State Space Models
taming-transformers
Taming Transformers for High-Resolution Image Synthesis
LRA-diffusion
This is the source code of LRA-diffusion for learning from noisy labels
diffusion-classifier
Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training
DiffMIC
[MICCAI 2023] DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
FROSTER
The official repository for ICLR2024 paper "FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition"
awesome-labels-learning
The papers and projects with multi-label learning
Vim
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
ICLR24
Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"
quilt1m
[NeurIPS 2023 Oral] Quilt-1M: One Million Image-Text Pairs for Histopathology.
PVT
Pyramid Transformer Networks for Our Own dataset.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
U-Mamba
U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
Conditional_Diffusion_MNIST
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
Regroup-Loss-Median-to-Combat-Label-Noise
Source code for AAAI-2024 Accepted paper Regroup Median Loss for Combating Label Noise