DeepBox: Learning Objectness with Convolutional Networks

Abstract

Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object proposals. Our framework, which we call DeepBox, uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method. We use a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster. We show that DeepBox significantly improves over the bottom-up ranking, achieving the same recall with 500 proposals as achieved by bottom-up methods with 2000. This improvement generalizes to categories the CNN has never seen before and leads to a 4.5-point gain in detection mAP. Our implementation achieves this performance while running at 260 ms per image.

ICCV 2015 Camera-ready version

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
• What makes for effective detection proposals?
• Learning to Segment Object Candidates
• Simultaneous Detection and Segmentation
• How good are detection proposals, really?

Cited by in corpus (12)

• Learning to Segment Object Candidates
• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
• Object Detection with Deep Learning: A Review
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
• Zoom Out-and-In Network with Recursive Training for Object Proposal
• ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
• Re-ranking Object Proposals for Object Detection in Automatic Driving
• Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
• DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
• Feature Selective Networks for Object Detection
• Toward Scale-Invariance and Position-Sensitive Region Proposal Networks