The Role of Context Selection in Object Detection

2016/09/09 by Ruichi Yu, Xi Chen, Yu, Ruichi +5 · 3 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.1609.02948

openalex publication_date 2016/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Rich feature hierarchies for accurate object detection and semantic\n segmentation

Cited by

• NISP: Pruning Networks using Neuron Importance Score Propagation
• Dynamic Zoom-in Network for Fast Object Detection in Large Images
• Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation

Related

• Exploring the Bounds of the Utility of Context for Object Detection
• Evaluating Context for Deep Object Detectors
• Exploring Person Context and Local Scene Context for Object Detection
• Context Forest for efficient object detection with large mixture models
• Contextual Object Detection with a Few Relevant Neighbors