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

arXiv: https://arxiv.org/abs/2001.04066 · HTML: https://mlsanity.com/paper/2001.04066/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

## Built on by (most cited first, 4 of 4)

- [SGNet: A Super-class Guided Network for Image Classification and Object Detection](https://mlsanity.com/paper/2104.12898/) (2021)
- [A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild](https://mlsanity.com/paper/2105.07625/) (2021)
- [A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation](https://mlsanity.com/paper/2110.10837/) (2021)
- [Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networks](https://mlsanity.com/paper/2102.05582/) (2021)

## Abstract (arXiv)

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 l1-norm and the squared l2-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.