ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

11/12/2015
by   Chen Sun, et al.
0

This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.

READ FULL TEXT

page 1

page 3

page 6

page 7

research
09/12/2016

A Multi-Scale Cascade Fully Convolutional Network Face Detector

Face detection is challenging as faces in images could be present at arb...
research
11/01/2017

Single Multi-feature detector for Amodal 3D Object Detection in RGB-D Images

This paper aims at fast and high-accuracy amodal 3D object detections in...
research
11/27/2017

Scalable Object Detection for Stylized Objects

Following recent breakthroughs in convolutional neural networks and mono...
research
06/20/2018

Weighted Hausdorff Distance: A Loss Function For Object Localization

Recent advances in Convolutional Neural Networks (CNN) have achieved rem...
research
05/25/2016

DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks

In this paper, we propose DeepCut, a method to obtain pixelwise object s...
research
12/07/2020

A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation

Object detection methods are widely adopted for computer-aided diagnosis...
research
09/30/2018

Correlation Propagation Networks for Scene Text Detection

In this work, we propose a novel hybrid method for scene text detection ...

Please sign up or login with your details

Forgot password? Click here to reset