Back to Search
Start Over
Group Sampling for Scale Invariant Face Detection
- Source :
- CVPR
- Publication Year :
- 2019
- Publisher :
- IEEE, 2019.
-
Abstract
- Detectors based on deep learning tend to detect multi-scale faces on a single input image for efficiency. Recent works, such as FPN and SSD, generally use feature maps from multiple layers with different spatial resolutions to detect objects at different scales, e.g., high-resolution feature maps for small objects. However, we find that such multi-layer prediction is not necessary. Faces at all scales can be well detected with features from a single layer of the network. In this paper, we carefully examine the factors affecting face detection across a large range of scales, and conclude that the balance of training samples, including both positive and negative ones, at different scales is the key. We propose a group sampling method which divides the anchors into several groups according to the scale, and ensure that the number of samples for each group is the same during training. Our approach using only the last layer of FPN as features is able to advance the state-of-the-arts. Comprehensive analysis and extensive experiments have been conducted to show the effectiveness of the proposed method. Our approach, evaluated on face detection benchmarks including FDDB and WIDER FACE datasets, achieves state-of-the-art results without bells and whistles.
- Subjects :
- business.industry
Computer science
Deep learning
Sampling (statistics)
020206 networking & telecommunications
Pattern recognition
Scale (descriptive set theory)
02 engineering and technology
Scale invariance
Categorization
Feature (computer vision)
Face (geometry)
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Face detection
business
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Accession number :
- edsair.doi...........384bb868146a377a1ee5c3fd0dbf617b