3 papers
cs.CV2026
Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection
Daeun Seo, Hoeseok Yang, Sihyeong Park +1
We propose Ciliary-DETR (previous name: Elastic-DETR), a framework for test-time resolution adjustment analogous to biological accommodation. While multi-scale data augmentation im…
cs.CV2024
Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing
Jaemin Kang, Hoeseok Yang, Hyungshin Kim
Deep learning has been successfully applied to object detection from remotely sensed images. Images are typically processed on the ground rather than on-board due to the computatio…
cs.CV2024
DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors
Daeun Seo, Hoeseok Yang, Hyungshin Kim
Achieving constant accuracy in object detection is challenging due to the inherent variability of object sizes. One effective approach to this problem involves optimizing input res…