# Scale-aware Automatic Augmentation for Object Detection

Source: [Scale-aware Automatic Augmentation for Object Detection](<https://www.sota2.com/research/paper/68fa69ad1e209131cea234ed>)

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

Data updated: 2026-01-04T05:05:09.654Z

Authors: Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya Jia

Published: 2021-03-31T17:11:14.000Z

## Abstract

We propose Scale-aware AutoAug to learn data augmentation policies for object detection. We define a new scale-aware search space, where both image- and box-level augmentations are designed for maintaining scale invariance. Upon this search space, we propose a new search metric, termed Pareto Scale Balance, to facilitate search with high efficiency. In experiments, Scale-aware AutoAug yields significant and consistent improvement on various object detectors (e.g., RetinaNet, Faster R-CNN, Mask R-CNN, and FCOS), even compared with strong multi-scale training baselines. Our searched augmentation policies are transferable to other datasets and box-level tasks beyond object detection (e.g., instance segmentation and keypoint estimation) to improve performance. The search cost is much less than previous automated augmentation approaches for object detection. It is notable that our searched policies have meaningful patterns, which intuitively provide valuable insight for human data augmentation design. Code and models will be available at https://github.com/Jia-Research-Lab/SA-AutoAug.

## 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 PASCAL VOC](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc.md>): Object Detection; Pascal VOC; mAP: 81.6.

- [Object Detection on MS COCO (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-ms-coco-test-dev.md>): Object Detection; MS COCO (test-dev); mAP@.5: 68.8.

- [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: 51.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.17220>)

[PDF](<https://arxiv.org/pdf/2103.17220.pdf>)

[Implementation](<https://github.com/Jia-Research-Lab/SA-AutoAug>)