Tavondo
HomeCompetitionsQuizGuidesPlatforms

No matching competitions

Try a platform, topic, or competition title

中文
HomeCompetitionsQuizGuidesPlatforms
中文RegisterSign in
Tavondo

Find AI contests that fit you—quiz, recommendations, catalog, and guides in one place.

Discover

CompetitionsQuizGuidesPlatforms

Account

Sign inRegisterSkill quiz

© 2026 Tavondo

中文
  1. Home
  2. Competitions
  3. 飞桨学习赛:文档检测优化赛

Competition workspace

Baidu AI StudioComputer VisionBeginnerRegistration unverifiedRegistration unverified

飞桨学习赛:文档检测优化赛

适合已有 Python 与计算机视觉基础、愿意使用 PaddlePaddle 训练端到端模型的个人开发者。尤其适合做过边缘检测、图像分割或关键点/角点回归,并能处理文档照片的候选人;比赛仅支持个人参赛。

Open official pageSign in to saveOpen guide

Suggested next step

Decide whether this contest fits your current stage before you sink time into the leaderboard.

Beginner score

78/100

Higher means a safer real starting point for your current stage.

Learning value

72/100

Measures whether the competition teaches habits you can transfer elsewhere.

Estimated effort

4-12 hours

Use this to check whether the task fits your current time budget.

Metric

Official scoring is published on the Ba…

If you cannot explain this metric clearly yet, you probably still need a bit of prep.

Who this competition fits

适合已有 Python 与计算机视觉基础、愿意使用 PaddlePaddle 训练端到端模型的个人开发者。尤其适合做过边缘检测、图像分割或关键点/角点回归,并能处理文档照片的候选人;比赛仅支持个人参赛。

Official blurb (unedited)
由百度网盘开放平台发起,通过模型算法实现文档边缘的识别监测。 Official tags: 图像处理. Sign-ups: 521.

What this competition gives you

There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.

BaselineForkable competition baseline notebook
TutorialVideo tutorial with score-improvement strategies
Data

Document-image dataset: 2,797 training and 597 test samples

Reference paperPixel Difference Networks for Efficient Edge Detection paper
Reference paperHolistically-Nested Edge Detection paper
BaselinePiDiNet open-source code reference
BaselineHEDNet open-source code reference

Prep before joining

If the items below still feel unfamiliar, you usually get a better result by preparing first instead of rushing in.

PaddlePaddle 2.0+

文档边缘检测

图像分割与热力图

四角点坐标回归

OpenCV 图像处理

Python 推理脚本与 ZIP 打包

Where the real difficulty shows up

The real friction is usually not library usage. It is validation, time allocation, and task framing.

难点不只是识别文档边缘,还要在真实拍摄背景下稳定定位文档四个角,并兼顾泛化效果与推理速度。若想取得更高分,页面明确建议直接回归四个角点;同时必须按指定的 predict.py、结果目录和 ZIP 结构提交可运行的模型。

Read this first

This guide is the best pre-read if you want a cleaner start instead of trial-and-error.

A pre-flight checklist for image competitions when you only have free cloud GPU access.

Your First CV Baseline Checklist

Your decision

Use these fields to make a quick decision before you dive deeper.

Status
Registration unverified
Registration
Registration unverified
Eligibility
Needs official confirmation
Reward
奖励积分
Compute
Free GPU OK
Official metric
Official scoring is published on the Baidu AI Studio competition page.
Verification
Source page verified

Registration is unverified; confirm availability on the official page before investing.

Save to account

Sign in to save competitions and build your own shortlist.

Sign in to saveCreate account

Official source

Rules, files, submission details, and the live deadline still come from the official page.

Open official page

Related competitions

These competitions share a similar domain or difficulty level.

Kaggle

Computer Vision

Digit Recognizer

Registration open

Kaggle

Computer Vision

Petals to the Metal - Flower Classification on TPU

Registration open

DrivenData

Computer Vision

Conser-vision Practice Area: Image Classification

Registration unverified

DrivenData

Computer Vision

Hateful Memes: Phase 1

Registration unverified

Data and review state

Separate what is confirmed from what still needs review. Official rules and deadlines win — report anything that looks wrong.

Source page verifiedMetric confirmedReviewed
Published on this site
Jul 21, 2026

Official metric is not published on the Baidu AI Studio competition listing; verify scoring on the competition page.