Reference : IML-GCN: Improved Multi-Label Graph Convolutional Network for Efficient yet Precise I...
Scientific congresses, symposiums and conference proceedings : Paper published in a journal
Engineering, computing & technology : Computer science
Security, Reliability and Trust
http://hdl.handle.net/10993/49421
IML-GCN: Improved Multi-Label Graph Convolutional Network for Efficient yet Precise Image Classification
English
Singh, Inder Pal mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Oyedotun, Oyebade mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Ghorbel, Enjie mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Aouada, Djamila mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Feb-2022
AAAI-22 Workshop Program-Deep Learning on Graphs: Methods and Applications
Yes
No
International
AAAI Conference on Artificial Intelligence Workshops
from 22-02-2022 to 01-03-2022
Association for the Advancement of Artificial Intelligence
Vancouver
Canada
[en] Computer Vision ; Graph Convolutional Network ; Multi-label Image Classification ; Machine Learning ; Deep Learning ; Artificial Intelligence
[en] In this paper, we propose the Improved Multi-Label Graph Convolutional Network (IML-GCN) as a precise and efficient framework for multi-label image classification. Although previous approaches have shown great performance, they usually make use of very large architectures. To handle this, we propose to combine the small version of a newly introduced network called TResNet with an extended version of Multi-label Graph Convolution Networks (ML-GCN); therefore ensuring the learning of label correlation while reducing the size of the overall network. The proposed approach considers a novel image feature embedding instead of using word embeddings. In fact, the latter are learned from words and not images making them inadequate for the task of multi-label image classification. Experimental results show that our framework competes with the state-of-the-art on two multi-label image benchmarks in terms of both precision and memory requirements.
SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg
Fonds National de la Recherche - FnR
Researchers ; Professionals ; Students
http://hdl.handle.net/10993/49421
This work was funded by the Luxembourg National Research Fund (FNR), under the project reference BRIDGES2020/IS/14755859/MEET-A/Aouada.

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
AAAI_IML_GCN__Camera_ready_.pdfThis work was funded by the Luxembourg National Research Fund (FNR), under the project reference BRIDGES2020/IS/14755859/MEET-A/AouadaAuthor postprint1.83 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.