HCOMP 2026 study: imagery scales skew annotator and reviewer performance
windx0303 · x · 2026-09-29
At HCOMP 2026, Priyankari Perali (UMD) presented "Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Scales In Aerial Damage Assessment," examining how image scale/resolution affects crowd annotator and reviewer performance in aerial damage assessment labeling.
More from Research
- Anthropic: Claude Autonomously Trains Models to Reliably Mitigate 10 Alignment Failures — inductionheads · 2026-09-29
- Palmer Luckey backs $10M XPRIZE to decode animal communication with AI — PeterDiamandis · 2026-09-29
- Self-play on board games distills superhuman CoT, lifting Qwen3-4B math average from 24.1 to 36.6 — PMinervini · 2026-09-29
- Qualification by Calibration: New Benchmark Audits LLM Annotators Like Crowd Workers — windx0303 · 2026-09-29
- LLM-Managed Papers Are Fine, But Author Names and Titles in Citations Are Wrong — erikphoel · 2026-09-29
- Evaluation Cards, an open standard for eval reporting, wins NeurIPS 2026 Spotlight — evijit · 2026-09-29