Pith. sign in

Improving single domain-generalized object detection: A focus on diversification and alignment

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic

cs.CV · 2025-06-26 · conditional · novelty 6.0

DuET is an exemplar-free task-arithmetic model-merging framework that performs simultaneous class- and domain-incremental object detection, validated on YOLO11 and RT-DETR, with a new directional consistency loss and a retention-adaptability metric.

citing papers explorer

Showing 1 of 1 citing paper.

  • DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic cs.CV · 2025-06-26 · conditional · none · ref 6

    DuET is an exemplar-free task-arithmetic model-merging framework that performs simultaneous class- and domain-incremental object detection, validated on YOLO11 and RT-DETR, with a new directional consistency loss and a retention-adaptability metric.