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

Abstract

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.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Pixel Recurrent Neural Networks
• MatConvNet - Convolutional Neural Networks for MATLAB
• Coherence-Based Performance Guarantees for Estimating a Sparse Vector Under Random Noise
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• Understanding intermediate layers using linear classifier probes
• Fast L1-Minimization Algorithms For Robust Face Recognition
• Facelet-Bank for Fast Portrait Manipulation

Cited by in corpus (13)

• A Comparative Study on Polyp Classification using Convolutional Neural Networks
• Deep Feature Augmentation for Occluded Image Classification
• MDFN: Multi-Scale Deep Feature Learning Network for Object Detection
• Plug-and-Play Rescaling Based Crowd Counting in Static Images
• Unsupervised Deep Feature Transfer for Low Resolution Image Classification
• SGNet: A Super-class Guided Network for Image Classification and Object Detection
• Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters
• Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images
• Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection
• Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networks
• Classification of Noncoding RNA Elements Using Deep Convolutional Neural Networks
• A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation