Sample and computation redistribution for efficient face detection
File(s)
Published version
Author(s)
Guo, Jia
Deng, Jiankang
Lattas, Alexandros
Zafeiriou, Stefanos
Type
Conference Paper
Abstract
Although tremendous strides have been made in uncontrolled face detection, accurate face detection with a low computation cost remains an open challenge. In this paper, we point out that computation distribution and scale augmentation are the keys to detecting small faces from low-resolution images. Motivated by these observations, we introduce two simple but effective methods: (1) Computation Redistribution (CR), which reallocates the computation between the backbone, neck and head of the model; and (2) Sample Redistribution (SR), which augments training samples for the most needed stages. The proposed Sample and Computation Redistribution for Face Detection (SCRFD) is implemented by a random search in a meticulously designed search space. Extensive experiments conducted on WIDER FACE demonstrate the state-of-the-art accuracy-efficiency trade-off for the proposed SCRFD family across a wide range of compute regimes. In particular, SCRFD-34GF outperforms the best competitor, TinaFace, by 4.78% (AP at hard set) while being more than 3× faster on GPUs with VGA-resolution images. Code is available at: https://github.com/deepinsight/insightface/tree/master/detection/scrfd.
Date Issued
2022-04-25
Date Acceptance
2022-04-01
Citation
International Conference on Learning Representations, 2022
Journal / Book Title
International Conference on Learning Representations
Copyright Statement
© 2022 The Author(s).
Identifier
http://arxiv.org/abs/2105.04714v1
Source
ICLR 2022 - 10th International Conference on Learning Representations
Subjects
cs.CV
cs.CV
Publication Status
Published
Start Date
2022-04-25
Finish Date
2022-04-29
Coverage Spatial
Virtual