AI Paper Atlas

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

AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection

Yipeng Gao, Lingxiao Yang, Yunmu Huang, Song Xie, Shiyong Li, Wei-Shi Zheng

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 42 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 adaptive optimization (filtering augmented samples) (ablation)AcroFOD with augmentation · C->FmAP50: 32.7 -> 41.1Improved
add multi-level domain-aware augmentation (ablation)AcroFOD with optimization · C->FmAP50: 26.4 -> 41.1Improved
add adaptive optimization (ablation)AcroFOD with augmentation · S->CAP50: 57.4 -> 62.5Improved
add augmentation (ablation)AcroFOD with optimization · K->CAP50: 51.9 -> 62.6Improved
add augmentation (ablation)AcroFOD with optimization · V->OAP50: 42.0 -> 45.8Improved
add adaptive optimization (ablation)AcroFOD with augmentation · V->OAP50: 41.4 -> 45.8Improved
use MMD instead of cosine distance for sample selection (ablation)AcroFOD · S->CAP50: 55.2 -> 55.6Improved
use MMD instead of cosine distance for sample selection (ablation)AcroFOD · K->CAP50: 51.4 -> 51.9Improved
add image-level domain-reallocation to domain-splice (ablation)AcroFOD · C->FmAP50: 27.5 -> 41.1Improved
add image-level domain-reallocation to domain-splice (ablation)AcroFOD · S->CAP50: 60.2 -> 62.3Improved
use proportional sampling of source and target dataYOLOv5 · S->CAP50: 49.0 -> 50.2Improved
use AcroFOD instead of Pre+FT with 1% COCO person dataYOLOv5 · V->O 1% dataAP50: 50.9 -> 61.1Improved

Later papers that compared with this method

2 later accepted papers report AcroFOD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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