AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets

Yuan-Hong Liao, David Acuna, Rafid Mahmood, James Lucas, Viraj Uday Prabhu, Sanja Fidler

ICLR 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces the label transfer problem for object detection to resolve annotation protocol mismatches across datasets by transferring labels between them.

Problem

Varying annotation protocols across object detection datasets cause inconsistent class labels and bounding regions, and fixing them manually is laborious.

Approach

Formulates label transfer as a new problem in object detection, aiming to automatically map and reconcile annotations between datasets with mismatched protocols, instead of manually identifying trends and fixing boxes and labels.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy