[1906.11172] Learning Data Augmentation Strategies for Object Detection

Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection. Given the additional cost for annotating images for object detection, data augmentation may be of even greater importance for this computer vision task. In this work, we study the impact of data augmentation on object detection. We first demonstrate that data augmentation operations borrowed from image classification may be helpful for training detection models, but the improvement is limited. Thus, we investigate how learned, specialized data augmentation policies improve generalization performance for detection models. Importantly, these augmentation policies only affect training and leave a trained model unchanged during evaluation. Experiments on the COCO dataset indicate that an optimized data augmentation policy improves detection accuracy by mor

7 mentions: @quocleix@yu4u@ekindogus@iamhimanshu_rai
Date: 2019/06/27 02:18

Referring Tweets

@quocleix We opensourced AutoAugment strategy for object detection. This strategy significantly improves detection models in our benchmarks. Please try it on your problems. Code: t.co/7iLsA4ZSCF Paper: t.co/2bee7rYr96 More details & results 👇 t.co/oYWLDV1vyA
@ekindogus Data augmentation is even more crucial for detection. We present AutoAugment for object detection, achieving SOTA on COCO validation set (50.7 mAP). Policy transfers to different models & datasets. Paper: t.co/Vu5Mqyj9qc, Code: t.co/ScLXqBAmnQ, details in thread. t.co/XZuyMjrxx8
@yu4u AutoAugmentの物体検出版だよー^^ / “[1906.11172] Learning Data Augmentation Strategies for Object Detection” t.co/s5CA9SZ8bh
@iamhimanshu_rai Policy transfers to different models & datasets. Paper: t.co/HzlkF8O26M , Code: t.co/7cdVcfO5dJ

Related Entries

Read more [1808.07632] DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN
0 users, 0 mentions 2018/08/25 21:22
Read more [1810.06826] Multi-Source Neural Machine Translation with Data Augmentation
0 users, 0 mentions 2018/10/30 19:17
Read more [1904.12848] Unsupervised Data Augmentation
0 users, 14 mentions 2019/04/30 02:17
Read more AutoML for Data Augmentation – Insight Data
0 users, 24 mentions 2019/03/27 15:25