Grid Loss: Detecting Occluded Faces

Abstract

Detection of partially occluded objects is a challenging computer vision problem. Standard Convolutional Neural Network (CNN) detectors fail if parts of the detection window are occluded, since not every sub-part of the window is discriminative on its own. To address this issue, we propose a novel loss layer for CNNs, named grid loss, which minimizes the error rate on sub-blocks of a convolution layer independently rather than over the whole feature map. This results in parts being more discriminative on their own, enabling the detector to recover if the detection window is partially occluded. By mapping our loss layer back to a regular fully connected layer, no additional computational cost is incurred at runtime compared to standard CNNs. We demonstrate our method for face detection on several public face detection benchmarks and show that our method outperforms regular CNNs, is suitable for realtime applications and achieves state-of-the-art performance.

accepted to ECCV 2016

References in corpus (5)

• Theano: new features and speed improvements
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Filtered Channel Features for Pedestrian Detection
• Taking a Deeper Look at Pedestrians

Cited by in corpus (7)

• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Face Detection through Scale-Friendly Deep Convolutional Networks
• From Facial Expression Recognition to Interpersonal Relation Prediction
• Adversarial Occlusion-aware Face Detection
• Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
• Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey