Pedestrian Detection with Unsupervised Multi-Stage Feature Learning
arXiv:1212.0142
Abstract
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.
12 pages
Cited by in corpus (15)
- Densely Connected Convolutional Networks
- Fully Convolutional Networks for Semantic Segmentation
- Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
- Unsupervised Learning of Visual Representations using Videos
- A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition
- Perceptual Generative Adversarial Networks for Small Object Detection
- Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Filtered Channel Features for Pedestrian Detection
- PANDA: Pose Aligned Networks for Deep Attribute Modeling
- Pedestrian Detection aided by Deep Learning Semantic Tasks
- PixelNN: Example-based Image Synthesis
- Contour Detection Using Cost-Sensitive Convolutional Neural Networks
- YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
- Multi-scale recognition with DAG-CNNs