Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection

04/27/2015
by   David Novotny, et al.
0

A novel efficient method for extraction of object proposals is introduced. Its "objectness" function exploits deep spatial pyramid features, a novel fast-to-compute HoG-based edge statistic and the EdgeBoxes score. The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM. State-of-the-art recall performance is achieved on Pascal VOC07, significantly outperforming methods with comparable speed. Interestingly, when only 100 proposals per image are considered the method attains 78 state-of-the-art class-specific detector, increasing it by 10 points when only 50 proposals are used in each image. The system trained on twenty classes performs well on the two hundred class ILSVRC2013 set confirming generalization capability.

READ FULL TEXT
research
04/03/2016

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

Almost all of the current top-performing object detection networks emplo...
research
02/20/2020

Learning Object Scale With Click Supervision for Object Detection

Weakly-supervised object detection has recently attracted increasing att...
research
06/26/2014

How good are detection proposals, really?

Current top performing Pascal VOC object detectors employ detection prop...
research
07/25/2018

Toward Scale-Invariance and Position-Sensitive Region Proposal Networks

Accurately localising object proposals is an important precondition for ...
research
07/12/2022

Dynamic Proposals for Efficient Object Detection

Object detection is a basic computer vision task to loccalize and catego...
research
09/08/2015

Object Proposals for Text Extraction in the Wild

Object Proposals is a recent computer vision technique receiving increas...
research
06/14/2017

SalProp: Salient object proposals via aggregated edge cues

In this paper, we propose a novel object proposal generation scheme by f...

Please sign up or login with your details

Forgot password? Click here to reset