R-FCN-3000 at 30fps: Decoupling Detection and Classification

12/05/2017
by   Bharat Singh, et al.
0

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness score with the fine-grained classification score. Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization. For fine-grained classification, these position-sensitive filters are not needed. R-FCN-3000 obtains an mAP of 34.9 on the ImageNet detection dataset and outperforms YOLO-9000 by 18 processing 30 images per second. We also show that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Code will be made available.

READ FULL TEXT

page 1

page 7

page 8

page 9

research
08/14/2019

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

Recent advances in deep learning greatly boost the performance of object...
research
12/10/2014

Object-centric Sampling for Fine-grained Image Classification

This paper proposes to go beyond the state-of-the-art deep convolutional...
research
12/22/2017

SFCN-OPI: Detection and Fine-grained Classification of Nuclei Using Sibling FCN with Objectness Prior Interaction

Cell nuclei detection and fine-grained classification have been fundamen...
research
08/07/2017

PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN

We aim to tackle a novel vision task called Weakly Supervised Visual Rel...
research
12/01/2022

On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection

State-of-the-art object detectors are fast and accurate, but they requir...
research
03/29/2016

Instance-sensitive Fully Convolutional Networks

Fully convolutional networks (FCNs) have been proven very successful for...
research
04/01/2019

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

We introduce a novel approach for keypoint detection task that combines ...

Please sign up or login with your details

Forgot password? Click here to reset