AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery

My Kieu, Andrew D. Bagdanov, Marco Bertini, Alberto del Bimbo

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 75 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add task-conditioning layers on detection heads (TC Det) (ablation)YOLOv3 thermal detector · KAIST nightlog-average miss rate: 16.69 -> 10.31Improved
add task-conditioning layers on detection heads (TC Det) (ablation)YOLOv3 thermal detector · KAIST day and nightlog-average miss rate: 31.06 -> 27.11Improved
condition residual groups instead of no conditioning (ablation)YOLOv3 thermal detector · KAIST day and nightlog-average miss rate: 31.06 -> 28.69Improved
condition all residual blocks (ablation)YOLOv3 thermal detector · KAIST day and nightlog-average miss rate: 31.06 -> 31.54Mixed
add residual group conditioning on top of detection head conditioning (ablation)TC Det · KAIST day and nightlog-average miss rate: 27.11 -> 30.48Hurt
fine-tune on visible images before thermal (no conditioning) (ablation)YOLOv3 thermal detector · KAIST day and nightlog-average miss rate: 31.06 -> 30.50Improved
add conditioning during visible stage (ablation)visible-then-thermal schedule · KAIST day and nightlog-average miss rate: 30.50 -> 28.48Improved
add conditioning during thermal stage (ablation)visible-then-thermal schedule · KAIST nightlog-average miss rate: 15.73 -> 11.03Improved
add conditioning in both visible and thermal stages (ablation)visible-then-thermal schedule · KAIST day and nightlog-average miss rate: 30.50 -> 27.11Improved
add conditioning to thermal-only adaptation without visible stage (ablation)YOLOv3 thermal detector · KAIST nightlog-average miss rate: 16.69 -> 12.61Improved
add conditioning to visible detector (ablation)YOLOv3 visible detector · KAIST visible testlog-average miss rate: 36.67 -> 34.73Improved
use TC Det (thermal only) versus Bottom-up adaptationYOLOv3 · KAIST nightlog-average miss rate: 20.50 -> 10.31Improved

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