.png){kind=icon}
Return
Deep feature augmentation for occluded image classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2020.107737.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the difficulty in acquiring massive task-specific occluded images, the classification of occluded images with deep convolutional neural networks (CNNs) remains highly challenging. To alleviate the dependency on large-scale occluded image datasets, we propose a novel approach to improve the classification accuracy of occluded images by fine-tuning the pre-trained models with a set of augmented deep feature vectors (DFVs). The set of augmented DFVs is composed of original DFVs and pseudo-DFVs. The pseudo-DFVs are generated by randomly adding difference vectors (DVs), extracted from a small set of clean and occluded image pairs, to the real DFVs. In the fine-tuning, the back-propagation is conducted on the DFV data flow to update the network parameters. The experiments on various datasets and network structures show that the deep feature augmentation significantly improves the classification accuracy of occluded images without a noticeable influence on the performance of clean images. Specifically, on the ILSVRC2012 dataset with synthetic occluded images, the proposed approach achieves 11.21% and 9.14% average increases in classification accuracy for the ResNet50 networks fine-tuned on the occlusion-exclusive and occlusion-inclusive training sets, respectively. (C) 2020 Elsevier Ltd. All rights reserved.
Keywords:
Deep feature augmentation
Image occlusion
Convolutional neural networks
Image classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
Learning robust and discriminative low-rank representations for face recognition with occlusion.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveDictionary Representation of Deep Features for Occlusion-Robust Face RecognitionIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSaveDiscriminative multi-scale sparse coding for single-sample face recognition with occlusionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more