Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
arXiv:1704.02431
Abstract
This paper presents a novel method for detecting pedestrians under adverse illumination conditions. Our approach relies on a novel cross-modality learning framework and it is based on two main phases. First, given a multimodal dataset, a deep convolutional network is employed to learn a non-linear mapping, modeling the relations between RGB and thermal data. Then, the learned feature representations are transferred to a second deep network, which receives as input an RGB image and outputs the detection results. In this way, features which are both discriminative and robust to bad illumination conditions are learned. Importantly, at test time, only the second pipeline is considered and no thermal data are required. Our extensive evaluation demonstrates that the proposed approach outperforms the state-of- the-art on the challenging KAIST multispectral pedestrian dataset and it is competitive with previous methods on the popular Caltech dataset.
Accepted at CVPR 2017
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Zero-Shot Learning Through Cross-Modal Transfer
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
- Ten Years of Pedestrian Detection, What Have We Learned?
- Filtered Channel Features for Pedestrian Detection
- Taking a Deeper Look at Pedestrians
Cited by in corpus (6)
- Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
- Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
- A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
- Graph Distillation for Action Detection with Privileged Modalities
- Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization