Paper Info
Title
Dynamic MLML-tree based adaptive object detection using heterogeneous data distribution
Abstract
We propose a robust object-detector ensemble by introducing a dynamic multi-layer multi-label (MLML)-tree–based adaptive deep learning framework. In many heterogeneous data distributions, deep attributes show latent hierarchical clustering properties. Object detector performance can be enhanced using the dynamic MLML-tree, which can adjust the ambiguities between inter-class nodes and variations between sub-class nodes. In the MLML-tree, dynamic multi-label (DML) trees are configured in two layers and adapt to using a sparse working dataset. First, coarse object clusters are built using an outlier-aware soft-clustering algorithm. Each coarse cluster is denoted by an inter-class node and is associated with an adaptive object detector in DML tree layer 1. It is built by recursively partitioning inter-class nodes until homogeneous object-class leaves are built. DML tree layer 2 is built for each object-class node, which is associated with a convolutional neural network detector, recursively. A novel sub-class can be learned automatically in DML tree layer 2 by applying semi-supervised learning. Extensive experiments show that the proposed method is superior to state-of-the-art techniques using PASCAL Visual Object Classes (VOC) 2007, VOC 2012, and the Microsoft Common Objects in Context (COCO) datasets.
Year
DOI
Venue
2020
10.1007/s11042-019-08285-7
Multimedia Tools and Applications
Keywords
Field
DocType
Deep learning, Convolutional neural network, Multi-layer multi-label, Object detection
Hierarchical clustering,Cluster (physics),Object detection,Pattern recognition,Computer science,Homogeneous,Convolutional neural network,Artificial intelligence,Deep learning,Detector,Recursion
Journal
Volume
Issue
ISSN
79
9
1380-7501
Citations 
PageRank 
References 
0
0.34
0
Authors
4
Name
Order
Citations
PageRank
Dong Kyun Shin100.34
Minhaz Uddin Ahmed273.40
Yeong Hyeon Kim300.34
Phill Kyu Rhee46024.82