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

Related tags

Deep Learning SCL
Overview

SCL

Introduction

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

We evaluated our approach using two baselines:

CANet [1] (project is here) and PFENet [2] (project is here).

Many thanks for their public project.

We followed the same setting with them.

You can follow the preparations of these two baselines, or you can find the running details in our documents.

References

[1] Chi Zhang, Guosheng Lin, Fayao Liu, Rui Yao, and Chunhua Shen. Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5217–5226, 2019.

[2] Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, and Jiaya Jia. Prior guided feature enrichment network for few-shot segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.

Comments
  • why did the model of SCL_PFENET trained by myself fail to achievel the performance of the paper? miou just 60.283

    why did the model of SCL_PFENET trained by myself fail to achievel the performance of the paper? miou just 60.283

    I download the paper code and trained the model (SCL PFENET ) for 200 epochs without any change, pytorch version is 1.6.0. But the best Miou is just 60.28

    Long before , I also trained PFENet by myself. And I got the similar results mIoU 61.4~61.6

    opened by TizzyTTT 12
  • I can't get a similar result as in the paper

    I can't get a similar result as in the paper

    First of all, thanks for publishing your source code. However, We tried to train the code without making any changes. Torch==1.9.0 and other environment configurations also meet the requirements. However, after 200 epochs, the best Miou is just 60.88. We use the Pascal-5i dataset, and the backbone is the resnet50 network, split=0. The best result we got was 60.88 instead of 63.0, which is written in the paper. We want to know what caused this result.

    opened by Hx111222 3
  • how to generate SegmentationClassAug?

    how to generate SegmentationClassAug?

    I have downloaded the PASCAL VOC 2012 dataset and SBD dataset from their official website respectively.But I donnot know how to use them in the code .Could you show me your dataset folder structure or the method to generate SegmentationClassAug?

    opened by WHL182 2
  • Evaluation iteration for COCO in 5-shot setting.

    Evaluation iteration for COCO in 5-shot setting.

    Thank you for your great work!

    You set the test_num=3000 (L175 in test_5shot.py) for COCO 5-shot scenario in PFENet, it is different with the original PFENet's setting and the 1-shot scenario, which is 20000. Should I use this setting (3000) or correct it (20000) for fair comparision with your method?

    opened by zhijiew 2
  • crop size in the training set

    crop size in the training set

    Hello. The crop size of the traing images is not mentioned in implementation details. Is it the same as the config file, train_h 473 for PASCAL and 641 for COCO?

    opened by tymatfd 1
  • The download links for the pre-trained model are not available

    The download links for the pre-trained model are not available

    Thank you for your great work!

    I'm checking your codes recently, but I can't download the pre-trained model from your links, it looks like some permission issue, can you check it or use some other service?

    Thanks!

    Xnip2021-06-30_12-27-15

    opened by zhijiew 1
  • PFE_SCL_1 shot_Training

    PFE_SCL_1 shot_Training

    Hello,

    Thank you for your wonderful work. While training your model. I just found this quotation. Can you please elaborate on why we are using the previous map instead of the current features map? Any ablation study?

    image

    opened by Ehteshamciitwah 0
Owner
null
[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Few-shot 3D Point Cloud Semantic Segmentation Created by Na Zhao from National University of Singapore Introduction This repository contains the PyTor

null 117 Dec 27, 2022
Official repository for Few-shot Image Generation via Cross-domain Correspondence (CVPR '21)

Few-shot Image Generation via Cross-domain Correspondence Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A. Efros, Yong Jae Lee, Eli Shechtman, Richard Zh

Utkarsh Ojha 251 Dec 11, 2022
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

T-Few This repository contains the official code for the paper: "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learni

null 220 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

cv516Buaa 9 Nov 7, 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

DV Lab 230 Dec 31, 2022
CVPR 2021 Official Pytorch Code for UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

UC2 UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training Mingyang Zhou, Luowei Zhou, Shuohang Wang, Yu Cheng, Linjie Li, Zhou Yu,

Mingyang Zhou 28 Dec 30, 2022
Few-NERD: Not Only a Few-shot NER Dataset

Few-NERD: Not Only a Few-shot NER Dataset This is the source code of the ACL-IJCNLP 2021 paper: Few-NERD: A Few-shot Named Entity Recognition Dataset.

THUNLP 319 Dec 30, 2022
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

null 233 Dec 29, 2022
The official implementation of the CVPR 2021 paper FAPIS: a Few-shot Anchor-free Part-based Instance Segmenter

FAPIS The official implementation of the CVPR 2021 paper FAPIS: a Few-shot Anchor-free Part-based Instance Segmenter Introduction This repo is primari

Khoi Nguyen 8 Dec 11, 2022
The Pytorch code of "Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification", CVPR 2022 (Oral).

DeepBDC for few-shot learning        Introduction In this repo, we provide the implementation of the following paper: "Joint Distribution Matters: Dee

FeiLong 116 Dec 19, 2022
Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, arXiv 2021

Hypercorrelation Squeeze for Few-Shot Segmentation This is the implementation of the paper "Hypercorrelation Squeeze for Few-Shot Segmentation" by Juh

Juhong Min 165 Dec 28, 2022
Implementation of the paper "Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning"

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning This is the implementation of the paper "Self-Promoted Prototype Refinement

Kai Zhu 78 Dec 2, 2022
Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

Cross Transformers - Pytorch (wip) Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch Install $ pip install cross-t

Phil Wang 40 Dec 22, 2022
Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

Region Proportion Regularized Inference (RePRI) for Few-Shot Segmentation In this repo, we provide the code for our paper : "Few-Shot Segmentation Wit

Malik Boudiaf 138 Dec 12, 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

Lucas 103 Dec 14, 2022
[CVPR 21] Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.

Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, CVPR 2021. Ayan Kumar Bhunia, Pinaki nath Chowdhury, Yongxin Yan

Ayan Kumar Bhunia 44 Dec 12, 2022
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss) This is the official pytorch implementation of our paper: "S2-BNN: Bridging th

Zhiqiang Shen 52 Dec 24, 2022
Self-training for Few-shot Transfer Across Extreme Task Differences

Self-training for Few-shot Transfer Across Extreme Task Differences (STARTUP) Introduction This repo contains the official implementation of the follo

Cheng Perng Phoo 33 Oct 31, 2022
Code and data of the ACL 2021 paper: Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

MetaAdaptRank This repository provides the implementation of meta-learning to reweight synthetic weak supervision data described in the paper Few-Shot

THUNLP 5 Jun 16, 2022