Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features

01/13/2020
by   Feng Cen, et al.
9

Classification of partially occluded images is a highly challenging computer vision problem even for the cutting edge deep learning technologies. To achieve a robust image classification for occluded images, this paper proposes a novel scheme using subspace decomposition based estimation (SDBE). The proposed SDBE-based classification scheme first employs a base convolutional neural network to extract the deep feature vector (DFV) and then utilizes the SDBE to compute the DFV of the original occlusion-free image for classification. The SDBE is performed by projecting the DFV of the occluded image onto the linear span of a class dictionary (CD) along the linear span of an occlusion error dictionary (OED). The CD and OED are constructed respectively by concatenating the DFVs of a training set and the occlusion error vectors of an extra set of image pairs. Two implementations of the SDBE are studied in this paper: the l_1-norm and the squared l_2-norm regularized least-squares estimates. By employing the ResNet-152, pre-trained on the ILSVRC2012 training set, as the base network, the proposed SBDE-based classification scheme is extensively evaluated on the Caltech-101 and ILSVRC2012 datasets. Extensive experimental results demonstrate that the proposed SDBE-based scheme dramatically boosts the classification accuracy for occluded images, and achieves around 22.25% increase in classification accuracy under 20% occlusion on the ILSVRC2012 dataset.

READ FULL TEXT

page 2

page 10

page 12

research
11/02/2020

Deep Feature Augmentation for Occluded Image Classification

Due to the difficulty in acquiring massive task-specific occluded images...
research
05/28/2019

Compositional Convolutional Networks For Robust Object Classification under Occlusion

Deep convolutional neural networks (DCNNs) are powerful models that yiel...
research
06/28/2020

Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion

Computer vision systems in real-world applications need to be robust to ...
research
02/02/2016

Head Pose Estimation of Occluded Faces using Regularized Regression

This paper presents regression methods for estimation of head pose from ...
research
08/07/2018

Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN

This paper introduces a Deep Learning Convolutional Neural Network model...
research
06/27/2023

See Through the Fog: Curriculum Learning with Progressive Occlusion in Medical Imaging

In recent years, deep learning models have revolutionized medical image ...
research
11/18/2019

Localizing Occluders with Compositional Convolutional Networks

Compositional convolutional networks are generative compositional models...

Please sign up or login with your details

Forgot password? Click here to reset