EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

Abstract

In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD),less than 0.1 million, as well as achieving comparable performance to deep heavy detectors. While existing multi-scale face detectors extract feature maps with different scales from a single backbone network, our method generates the feature maps by iteratively reusing a shared lightweight and shallow backbone network. This iterative sharing of the backbone network significantly reduces the number of parameters, and also provides the abstract image semantics captured from the higher stage of the network layers to the lower-level feature map. The proposed idea is employed by various model architectures and evaluated by extensive experiments. From the experiments from WIDER FACE dataset, we show that the proposed face detector can handle faces with various scale and conditions, and achieved comparable performance to the more massive face detectors that few hundreds and tens times heavier in model size and floating point operations.

References in corpus (23)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Densely Connected Convolutional Networks
• YOLO9000: Better, Faster, Stronger
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Face Detection through Scale-Friendly Deep Convolutional Networks
• NSML: Meet the MLaaS platform with a real-world case study
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• Detecting Faces Using Region-based Fully Convolutional Networks
• Face Detection Using Improved Faster RCNN
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• ThunderNet: Towards Real-time Generic Object Detection
• Anchor Cascade for Efficient Face Detection
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Depthwise Convolution is All You Need for Learning Multiple Visual Domains
• Improved Selective Refinement Network for Face Detection
• IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
• Selective Refinement Network for High Performance Face Detection
• ShaResNet: reducing residual network parameter number by sharing weights

Cited by in corpus (11)

• Tiny Machine Learning: Progress and Futures
• TinaFace: Strong but Simple Baseline for Face Detection
• Going Deeper Into Face Detection: A Survey
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
• Fine-Grained Crowd Counting
• RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
• ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules
• ASFD: Automatic and Scalable Face Detector
• Face Detection with Feature Pyramids and Landmarks
• SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution