The Role of Context Selection in Object Detection
arXiv:1609.02948
Abstract
We investigate the reasons why context in object detection has limited utility by isolating and evaluating the predictive power of different context cues under ideal conditions in which context provided by an oracle. Based on this study, we propose a region-based context re-scoring method with dynamic context selection to remove noise and emphasize informative context. We introduce latent indicator variables to select (or ignore) potential contextual regions, and learn the selection strategy with latent-SVM. We conduct experiments to evaluate the performance of the proposed context selection method on the SUN RGB-D dataset. The method achieves a significant improvement in terms of mean average precision (mAP), compared with both appearance based detectors and a conventional context model without the selection scheme.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Cross Modal Distillation for Supervision Transfer
Cited by in corpus (7)
- Learning Rich Features for Image Manipulation Detection
- NISP: Pruning Networks using Neuron Importance Score Propagation
- Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
- Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
- Dynamic Zoom-in Network for Fast Object Detection in Large Images
- Deep Regionlets for Object Detection