AI Paper Atlas

Research map / Detection and segmentation / CNN features

Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification

Hang Xu, Lewei Yao, Wei Zhang, Xiaodan Liang, Zhenguo Li

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 233 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
search Auto-FPN architecture (neck and head) instead of FPNFPN · COCO minvalmAP: 38.6 -> 40.5Improved
search Auto-FPN architecture instead of FPNFPN · PASCAL VOCmAP: 79.7 -> 81.8Improved
search Auto-FPN architecture instead of FPNFPN · BDDmAP: 33.0 -> 33.9Improved
use Auto-FPN with ResNet-101 instead of FPNFPN ResNet-101 · COCOmAP: 40.7 -> 42.5Improved
transfer COCO-searched architecture to Visual GenomeFPN · Visual GenomemAP: 7.0 -> 7.2Improved
transfer COCO-searched architecture to ADEFPN · ADEmAP: 10.5 -> 12.1Improved
apply Auto-fusion to SSD512SSD512 · COCOmAP: 29.3 -> 31.8Improved
apply Auto-fusion to SSD512SSD512 · PASCAL VOCmAP: 79.8 -> 79.9No clear effect
add step training (optimize architecture parameters in the middle of search) (ablation)Auto-fusion · PASCAL VOC (search)mAP: 81.7 -> 82.2Improved
freeze the backbone during search (ablation)Auto-fusion · PASCAL VOC (search)mAP: 65.2 -> 82.2Improved
search without batch norm (versus with BN) (ablation)Auto-head · PASCAL VOC (search)mAP: 78.3 -> 81.3Improved
load pretrained neck when searching head (ablation)Auto-head · PASCAL VOC (search)mAP: 78.4 -> 81.3Improved

Later papers that compared with this method

2 later accepted papers report Auto-FPN as a baseline in their results tables; 2 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