SOTAVerified

A Strong and Reproducible Object Detector with Only Public Datasets

2023-04-25Code Available2· sign in to hype

Tianhe Ren, Jianwei Yang, Shilong Liu, Ailing Zeng, Feng Li, Hao Zhang, Hongyang Li, Zhaoyang Zeng, Lei Zhang

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

This work presents Focal-Stable-DINO, a strong and reproducible object detection model which achieves 64.6 AP on COCO val2017 and 64.8 AP on COCO test-dev using only 700M parameters without any test time augmentation. It explores the combination of the powerful FocalNet-Huge backbone with the effective Stable-DINO detector. Different from existing SOTA models that utilize an extensive number of parameters and complex training techniques on large-scale private data or merged data, our model is exclusively trained on the publicly available dataset Objects365, which ensures the reproducibility of our approach.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
COCO minivalFocal-Stable-DINO (Focal-Huge, no TTA)box AP64.6Unverified
COCO test-devFocal-Stable-DINO (Focal-Huge, no TTA)box mAP64.8Unverified

Reproductions