AI Paper Atlas

Research map / Detection and segmentation / CNN features

Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

Yifan Feng, Jiangang Huang, Shaoyi Du, Shihui Ying, Jun‐Hai Yong, Yipeng Li, Guiguang Ding, Rongrong Ji, Yue Gao

TPAMI 2024 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 485 citations (OpenAlex)

Read the paper

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
replace C2f with MANet block (ablation)Hyper-YOLO-S backbone · COCO val2017AP val: 44.9 -> 46.4Improved
use kernels [3,5,5,3] instead of all 3 (ablation)MANet backbone · COCO val2017AP val: 46.3 -> 46.4Improved
use all-5 kernels instead of [3,5,5,3] (ablation)MANet backbone · COCO val2017AP val: 46.4 -> 46.6No clear effect
add low-order graph learning in the neck (ablation)Hyper-YOLO-S · COCO val2017AP val: 46.4 -> 47.6Improved
use high-order hypergraph instead of low-order graph learning (ablation)Hyper-YOLO-S · COCO val2017AP val: 47.6 -> 48.0Improved
increase semantic collecting inputs from 3 to 5 levels (ablation)Hyper-YOLO-S · COCO val2017AP val: 47.5 -> 48.0Improved
distance threshold 8 instead of 6 (ablation)hypergraph construction · COCO val2017AP val: 47.6 -> 48.0Improved
distance threshold 8 instead of 10 (ablation)hypergraph construction · COCO val2017AP val: 47.7 -> 48.0Improved
add hypergraph computation vs none (ablation)Hyper-YOLO-S · COCO val2017AP val: 46.3 -> 48.0Improved
add backbone enhancement to YOLOv8-N (ablation)Hyper-YOLO-N · COCO val2017AP val: 37.3% -> 39.9%Improved
add neck enhancement after backbone (ablation)Hyper-YOLO-N · COCO val2017AP val: 39.9% -> 41.8%Improved
add backbone enhancement to YOLOv8-L (ablation)Hyper-YOLO-L · COCO val2017AP val: 52.9% -> 53.0%No clear effect

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