DeepBox: Learning Objectness with Convolutional Networks

05/08/2015
by   Weicheng Kuo, et al.
0

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.

READ FULL TEXT

page 2

page 5

research
01/24/2019

Object Detection based on Region Decomposition and Assembly

Region-based object detection infers object regions for one or more cate...
research
11/11/2013

Rich feature hierarchies for accurate object detection and semantic segmentation

Object detection performance, as measured on the canonical PASCAL VOC da...
research
08/13/2020

What leads to generalization of object proposals?

Object proposal generation is often the first step in many detection mod...
research
12/03/2014

Scalable, High-Quality Object Detection

Current high-quality object detection approaches use the scheme of salie...
research
02/05/2015

Object Proposal with Kernelized Partial Ranking

Object proposals are an ensemble of bounding boxes with high potential t...
research
04/11/2017

Learning Detection with Diverse Proposals

To predict a set of diverse and informative proposals with enriched repr...
research
01/26/2019

4D Generic Video Object Proposals

Many high-level video understanding methods require input in the form of...

Please sign up or login with your details

Forgot password? Click here to reset