Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision

Abstract

The performance of face detectors has been largely improved with the development of convolutional neural network. However, it remains challenging for face detectors to detect tiny, occluded or blurry faces. Besides, most face detectors can't locate face's position precisely and can't achieve high Intersection-over-Union (IoU) scores. We assume that problems inside are inadequate use of supervision information and imbalance between semantics and details at all level feature maps in CNN even with Feature Pyramid Networks (FPN). In this paper, we present a novel single-shot face detection network, named DF${}^2$S${}^2$ (Detection with Feature Fusion and Segmentation Supervision), which introduces a more effective feature fusion pyramid and a more efficient segmentation branch on ResNet-50 to handle mentioned problems. Specifically, inspired by FPN and SENet, we apply semantic information from higher-level feature maps as contextual cues to augment low-level feature maps via a spatial and channel-wise attention style, preventing details from being covered by too much semantics and making semantics and details complement each other. We further propose a semantic segmentation branch to best utilize detection supervision information meanwhile applying attention mechanism in a self-supervised manner. The segmentation branch is supervised by weak segmentation ground-truth (no extra annotation is required) in a hierarchical manner, deprecated in the inference time so it wouldn't compromise the inference speed. We evaluate our model on WIDER FACE dataset and achieved state-of-art results.

arXiv comment10 pages, 4 figures. arXiv admin note: text overlap with arXiv:1711.07246, arXiv:1712.00721 by other authors

References in corpus (17)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Deep Residual Learning for Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Focal Loss for Dense Object Detection
• Recurrent Models of Visual Attention
• Fully Convolutional Networks for Semantic Segmentation
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Feature Pyramid Networks for Object Detection
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Face Detection through Scale-Friendly Deep Convolutional Networks
• PyramidBox: A Context-assisted Single Shot Face Detector
• Improved Selective Refinement Network for Face Detection
• Seeing Small Faces from Robust Anchor's Perspective
• Single-Shot Object Detection with Enriched Semantics
• Face R-CNN

Cited by in corpus (9)

• RetinaFace: Single-stage Dense Face Localisation in the Wild
• TinaFace: Strong but Simple Baseline for Face Detection
• D${}^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios
• YOLO5Face: Why Reinventing a Face Detector
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• Improved Selective Refinement Network for Face Detection
• Accurate Face Detection for High Performance
• RefineFace: Refinement Neural Network for High Performance Face Detection
• MaskFace: multi-task face and landmark detector