Dense Gaussian Processes for Few-Shot Segmentation

Last update: Jan 07, 2023

Related tags

Deep Learning DGPNet

Overview

DGPNet - Dense Gaussian Processes for Few-Shot Segmentation

Welcome to the public repository for DGPNet. The paper is available at arxiv: https://arxiv.org/abs/2110.03674 .

How to run

Download data

Download and unzip PASCAL and COCO images
Download and unzip PASCAL and COCO annotations (we provide link here)
Change local_config.py to point out the images and annotations. Also change slurm_launch.sh if using slurm.
Download and unzip PASCAL and COCO data splits (we provide link here)
Make sure that the data splits are at DGPNet/data_splits

Install dependencies

The dependencies are listed in DGPNet/singularity/Dockerfile21.09

Train and test model

We typically run via slurm, using

sbatch singularity/slurm_launch.sh runfiles/dgp_5shot_pascal_resnet50.py --train --test --dataset pascal --fold 0 --add_packages_to_path

Code layout

checkpoints - Checkpoints will be stored here at the end of training.
data_splits - Defines the different folds.
fss - Code is here.
local_config.py - Used to set up paths
logs - Used to store slurm checkpoints
runfiles - Any experiment we run is defined in a runfile. The runfile is launched as main to start the experiment.
singularity - We use singularity/slurm and any files related to that are stored here.
visualization - During training and testing, our code stores some visualizations. They go here.

Code for 'Self-Guided and Cross-Guided Learning for Few-shot segmentation. (CVPR' 2021)'

SCL Introduction Code for 'Self-Guided and Cross-Guided Learning for Few-shot segmentation. (CVPR' 2021)' We evaluated our approach using two baseline

34 Oct 8, 2022

Official code for "Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer. ICCV2021".

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer. ICCV2021. Introduction We proposed a novel model training paradi

103 Dec 14, 2022

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

PFENet This is the implementation of our paper PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation that has been accepted to IEE

230 Dec 31, 2022

The code is for the paper "A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation"

SD-AANet The code is for the paper "A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation" [arxiv] Overview confi

9 Nov 7, 2022

CharacterGAN: Few-Shot Keypoint Character Animation and Reposing

CharacterGAN Implementation of the paper "CharacterGAN: Few-Shot Keypoint Character Animation and Reposing" by Tobias Hinz, Matthew Fisher, Oliver Wan

181 Dec 27, 2022

Few-shot Learning of GPT-3

Few-shot Learning With Language Models This is a codebase to perform few-shot "in-context" learning using language models similar to the GPT-3 paper.

224 Dec 28, 2022

Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification.

Easy Few-Shot Learning Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification. This repository is made for you

399 Jan 8, 2023

git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021) This repo contains the implementation of our state-of-the-art fewshot ob

233 Dec 29, 2022

Library of various Few-Shot Learning frameworks for text classification

FewShotText This repository contains code for the paper A Neural Few-Shot Text Classification Reality Check Environment setup # Create environment pyt

47 Jan 3, 2023

Comments

how to visualise the Gaussian process?

Hi there, I think your idea of using GP is very interesting. May I know how you visualize the Gaussian mean and covariance in the overview figure (Figure2 in the latest Arvix version)? Thanks in advance.

opened by ry-jojo 4
torch.linalg.cholesky warnings

Hi Joakim, When training on 10shot, I am facing with warnings like the below:

WARNING batched routines are designed for small sizes. It might be better to use the Native/Hybrid classical routines if you want good performance.

I think this warning comes from the torch.linalg.cholesky(K_ss), when K_ss's largest size() > 2048.

May I know how you deal with this warning during training? Thanks in advance!

opened by ry-jojo 2

Dense Gaussian Processes for Few-Shot Segmentation

Related tags

Overview

DGPNet - Dense Gaussian Processes for Few-Shot Segmentation

How to run

Download data

Install dependencies

Train and test model

Code layout

You might also like...

Code for 'Self-Guided and Cross-Guided Learning for Few-shot segmentation. (CVPR' 2021)'

Official code for "Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer. ICCV2021".

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

The code is for the paper "A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation"

CharacterGAN: Few-Shot Keypoint Character Animation and Reposing

Few-shot Learning of GPT-3

Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification.

git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]

Library of various Few-Shot Learning frameworks for text classification

Comments

how to visualise the Gaussian process?

torch.linalg.cholesky warnings

Releases(eccv_video_and_poster)

eccv_video_and_poster(Sep 28, 2022)

Owner

Implementation of a protein autoregressive language model, but with autoregressive infilling objective (editing subsequences capability)

Code implementation of Data Efficient Stagewise Knowledge Distillation paper.

Code for "Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification", ECCV 2020 Spotlight

PaRT: Parallel Learning for Robust and Transparent AI

Official PyTorch implementation of Joint Object Detection and Multi-Object Tracking with Graph Neural Networks

Improved Fitness Optimization Landscapes for Sequence Design

Pywonderland - A tour in the wonderland of math with python.

B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

dyld_shared_cache processing / Single-Image loading for BinaryNinja

Official implementation of Self-supervised Image-to-text and Text-to-image Synthesis

The PyTorch implementation of paper REST: Debiased Social Recommendation via Reconstructing Exposure Strategies

Transport Mode detection - can detect the mode of transport with the help of features such as acceeration,jerk etc

Learning Saliency Propagation for Semi-supervised Instance Segmentation

A transformer-based method for Healthcare Image Captioning in Vietnamese

SoGCN: Second-Order Graph Convolutional Networks

Code accompanying the paper Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs (Chen et al., CVPR 2020, Oral).

Simple converter for deploying Stable-Baselines3 model to TFLite and/or Coral

Projects of Andfun Yangon