# Simple Training Strategies and Model Scaling for Object Detection

Source: [Simple Training Strategies and Model Scaling for Object Detection](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:31:36.648Z

Authors: Xianzhi Du, Barret Zoph, Wei-Chih Hung, Tsung-Yi Lin

Published: 2021-06-30T18:41:47.000Z

## Abstract

The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from. We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors. The vanilla detectors are improved by 7.7% in accuracy while being 30% faster in speed. We further provide simple scaling strategies to generate family of models that form two Pareto curves, named RetinaNet-RS and Cascade RCNN-RS. These simple rescaled detectors explore the speed-accuracy trade-off between the one-stage RetinaNet detectors and two-stage RCNN detectors. Our largest Cascade RCNN-RS models achieve 52.9% AP with a ResNet152-FPN backbone and 53.6% with a SpineNet143L backbone. Finally, we show the ResNet architecture, with three minor architectural changes, outperforms EfficientNet as the backbone for object detection and instance segmentation systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on Waymo Open Dataset](<https://www.sota2.com/research/sota/object-detection-on-waymo-open-dataset.md>): Object Detection; Waymo Open Dataset; AP (L1): 71.2.

- [Instance Segmentation on COCO 2017 (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-2017-val.md>): Instance Segmentation; COCO 2017 (val); APm: 0.567.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 52.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.00057>)

[PDF](<https://arxiv.org/pdf/2107.00057.pdf>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/vision/beta>)