Papers › DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors

DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors

28 Nov 2023arXiv:2311.17098archive 2025-07-28

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 resolution, referred to as a multi-resolution strategy. Previous approaches to resolution optimization have often been based on pre-defined resolutions with manual selection. However, there is a lack of study on run-time resolution optimization for existing architectures. This paper introduces DyRA, a dynamic resolution adjustment network providing an image-specific scale factor for existing detectors. This network is co-trained with detectors utilizing specially designed loss functions, namely ParetoScaleLoss and BalanceLoss. ParetoScaleLoss determines an adaptive scale factor for robustness, while BalanceLoss optimizes overall scale factors according to the localization performance of the detector. The loss function is devised to minimize the accuracy drop across contrasting objectives of different-sized objects for scaling. Our proposed network can improve accuracy across various models, including RetinaNet, Faster-RCNN, FCOS, DINO, and H-Deformable-DETR. The code is available at https://github.com/DaEunFullGrace/DyRA.git.

PaperPDFCode

Code

daeunfullgrace/dyra officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject DetectionRobust Object Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAttentionConvolutionDINODense ConnectionsFCOSFPNFocal LossLayer NormalizationLinear LayerMulti-Head AttentionNon Maximum SuppressionResidual ConnectionRetinaNetSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections