Coder Social home page Coder Social logo

ezra-yu / accv2022_fgia_1st Goto Github PK

View Code? Open in Web Editor NEW
32.0 3.0 1.0 35.55 MB

1st solution for the Webly-supervised Fine-grained Recognition competition in https://www.cvmart.net/race/10412/base

Python 95.22% Shell 4.20% Dockerfile 0.58%
arcface-loss eql fine-grained-classification longtail mae pseudolabelling pytorch swin

accv2022_fgia_1st's Introduction

Solution of FGIA ACCV 2022(1st Place)

This is the 1st Place Solution for Webly-supervised Fine-grained Recognition, refer to the ACCV workshop competition in https://www.cvmart.net/race/10412/base.

Mainly done by Ezra-Yu, Yuan Liu and Songyang Zhang, base on MMClassifiionMMSelfSup. please flork and star them if you think they are useful.

Lecture and slide are available.

Note:

Tricks (AdaptiveSubCenterArcFace, EQL_Loss, Post-Hoc_LT_Adjusment, Uniform_Model_Soup) have been or will be implemented in MMClassifiion.

Result

Show the result

LB A

LB-A

LB B

LB-B


Reproduce / 复现

复现精度请点击这里

Description

Backbone and Pre-train

Archs

  • ViT + CE-loss + post-LongTail-Adjusment
  • ViT + SubCenterArcFaceWithAdvMargin(CE)
  • Swin-B + SubCenterArcFaceWithAdvMargin(SoftMax-EQL)
  • Swin-L + SubCenterArcFaceWithAdvMargin(SoftMAx-EQL)

所有都使用了 Flip TTA

Flow

MIM 预训练 --> 训练 --> 清洗数据 --> fine-tune + 集成 + 生成伪标签交替训练 --> 后处理

  1. MAE 预训练
  2. Swin 与 ViT 的训练
  3. 使用权重做数据清洗
  4. 训练 -> 制作伪标签,放回训练集中 -> 再训练; (testa3轮)
  5. 训练 -> 制作伪标签,放回训练集中 -> 再训练; (testb3轮,包括testa的伪标签)
  6. 模型融合,调整预测的标签分布,提交

flow

Summary

image

使用了没有效果 used but no improvement

  1. 使用检索以及检索分类混合的方式
  2. 使用EfficientNet

后续 not used but worth try

  1. DiVE 蒸馏提升长尾问题表现
  2. Simim 训一个 swinv2 的预训练模型
  3. 优化 re-distribute-label

accv2022_fgia_1st's People

Contributors

ezra-yu avatar yuanliuuuuuu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

Forkers

wangjinghuacom

accv2022_fgia_1st's Issues

关于数据集的问题

请问这次比赛的数据集还有其他下载途径吗?官网只能报名才能下载数据集,但报名时间早已经过去了。

关于自蒸馏

image
流程中的自蒸馏的代码在哪儿,是指使用伪标签训练么?

关于MAE的疑问

@Ezra-Yu 非常感谢您的工作。当前有些疑问,麻烦解惑~

目的:MAE预训练的资源和成本过高,想了解收益如何?
问题:MAE是否有消融实验结果?如果没有,MAE-ViT在比赛过程中的提升过程也OK~

再次感谢,期待回复~

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.