Computer VisionEndedHateful Memes: Phase 1
Official page previewCaptured Oct 19 · not live
Open the competition on DrivenData↗
Open the competition on DrivenData↗- Effort
- 6–16 hours
- Difficulty
- Beginner
- Compute
- Free GPU OK
- Scoring
- Automatic
About the task
Full rules ↗Detecting hateful content presents a unique challenge in memes, where multiple data modalities need to be analyzed together. Facebook is calling on researchers around the world to help identify which memes contain hate speech.
- Scoring
- “Model performance and leaderboard rankings will be determined using the AUC ROC , or…” The official page's words
- Host
Is it for you?
Strong first competition
Beginner fit82/100
Learning value86/100
Getting startedRunnable baseline
From the organizer
- BaselineBaseline models supplied with the challenge
- BaselinePrize-winning competition models on GitHub ↗
- DataHateful Memes multimodal meme dataset
- PaperHateful Memes dataset release paper ↗
- PaperNeurIPS competition report ↗
First competition? Read Your First CV Baseline Checklist