YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

Hugging Face Daily Papers Papers
parameter-efficient-fine-tuning yolo object-detection adapter-placement lora fine-tuning

Summary

YOLO-PEFT is a structure-aware framework that formulates adapter placement as constraint planning for parameter-efficient fine-tuning of YOLO detectors, achieving better mAP than full fine-tuning with reduced memory.

Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous operators and detection-specific components impose placement constraints absent from regular Transformer stacks. We propose YOLO-PEFT, a structure-aware framework that formulates adapter placement as an auditable constraint-planning problem. Given a detector graph, a PEFT request, and a resource budget, YOLO-PEFT assigns operator and semantic roles, evaluates explicit operator-validity, detector-semantic, graph-interface, and deployment predicates, records a reason code for each excluded module, and either emits a budgeted target-module plan or returns Refuse before training. Under the official VOC07+12 trainval-to-VOC07 test protocol, planner-selected RS-LoRA reaches 0.7138 and 0.7307 mAP50-95 on YOLO11s and YOLO12s, respectively, compared with 0.6428 and 0.6662 for Full-SFT. On RT-DETR-L, all seven evaluated LoRA-family configurations cross the predefined catastrophic threshold, supporting a calibrated Refuse-to-Full-SFT decision within the evaluated coverage. A controlled YOLO11 audit further shows that LoRA reduces peak training memory by 43.9 percent, although training takes 1.72 times longer. Within the evaluated detector families, placement policies, and calibration coverage, YOLO-PEFT replaces manual target-module trial and error with explicit, inspectable planning while preserving verified train-save-merge-export paths; refusal on unseen detector architectures remains an open validation problem. Project Page: github.com/Tencent/YOLO-Master
Original Article
View Cached Full Text

Cached at: 08/10/26, 06:13 AM

Paper page - YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

Source: https://huggingface.co/papers/2608.07051

Abstract

Genericparameter-efficientfine-tuning(PEFT)methodstransferredfromlanguagemodelscanfailsilentlyonreal-timedetectors,whoseheterogeneousoperatorsanddetection-specificcomponentsimposeplacementconstraintsabsentfromregularTransformerstacks.WeproposeYOLO-PEFT,astructure-awareframeworkthatformulatesadapterplacementasanauditableconstraint-planningproblem.Givenadetectorgraph,aPEFTrequest,andaresourcebudget,YOLO-PEFTassignsoperatorandsemanticroles,evaluatesexplicitoperator-validity,detector-semantic,graph-interface,anddeploymentpredicates,recordsareasoncodeforeachexcludedmodule,andeitheremitsabudgetedtarget-moduleplanorreturnsRefusebeforetraining.UndertheofficialVOC07+12trainval-to-VOC07testprotocol,planner-selectedRS-LoRAreaches0.7138and0.7307mAP50-95onYOLO11sandYOLO12s,respectively,comparedwith0.6428and0.6662forFull-SFT.OnRT-DETR-L,allsevenevaluatedLoRA-familyconfigurationscrossthepredefinedcatastrophicthreshold,supportingacalibratedRefuse-to-Full-SFTdecisionwithintheevaluatedcoverage.AcontrolledYOLO11auditfurthershowsthatLoRAreducespeaktrainingmemoryby43.9percent,althoughtrainingtakes1.72timeslonger.Withintheevaluateddetectorfamilies,placementpolicies,andcalibrationcoverage,YOLO-PEFTreplacesmanualtarget-moduletrialanderrorwithexplicit,inspectableplanningwhilepreservingverifiedtrain-save-merge-exportpaths;refusalonunseendetectorarchitecturesremainsanopenvalidationproblem.ProjectPage:github.com/Tencent/YOLO-Master

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.07051

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.07051 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.07051 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.07051 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles