Deep Feature Augmentation for Occluded Image Classification

@article{Cen2020DeepFA,
  title={Deep Feature Augmentation for Occluded Image Classification},
  author={Feng Cen and Xiaoyu Zhao and Wuzhuang Li and Guanghui Wang},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.00768}
}

A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

A comprehensive survey of image augmentation for deep learning using a novel informative taxonomy is performed and it is believed that the survey enhances the understanding necessary for choosing suitable methods and designing novel algorithms.

Data Augmentation Using Mixup and Random Erasing

This paper proposes two different combinations of these two methods, namely RSM and RDM, to compensate their respective shortcomings for object detection and image classification on various datasets.

Efficient residual attention network for single image super-resolution

A channel hourglass residual structure (CHRS), consisting of several nested residual modules, is developed to learn more discriminative representations with fewer model parameters, and the ECA is presented to efficiently capture local cross-channel interaction by subtly applying 1D convolution.

Efficient residual attention network for single image super-resolution

A channel hourglass residual structure (CHRS), consisting of several nested residual modules, is developed to learn more discriminative representations with fewer model parameters, and the ECA is presented to efficiently capture local cross-channel interaction by subtly applying 1D convolution.

Correlation-based structural dropout for convolutional neural networks

A Discriminative Channel Diversification Network for Image Classification

Channel Hourglass Residual Network For Single Image Super-Resolution

This paper designs channel hourglass residual structure (CHRS) consisted of several nested residual modules for reducing parameters and extracting more representational features and proposes channel hour glass residual network (CHRN) which not only pays attention to network learning efficiency but also learns more discriminative expressions.

DATA AUGMENTATION FOR A LEARNING-BASED VEHICLE MAKE-MODEL AND LICENSE PLATE MATCHING SYSTEM

The proposed approach which has been used in creating the dataset is presented in detail and the generated new vehicle image dataset is available to developers as open-source.

Improving Multiscale Object Detection With Off-Centered Semantics Refinement

A new feature pyramid architecture named Off-Centered Semantics Refinement Feature Pyramid Network (OSR-FPN) is proposed, and the Sigmoid-interpolation Padding method to enhance the authors' OSR.

Audio-Visual Transformer Based Crowd Counting

A new audiovisual multi-task network is proposed to address the critical challenges in crowd counting by effectively utilizing both visual and audio inputs for better modalities association and productive feature extraction.

References

SHOWING 1-10 OF 51 REFERENCES

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

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.

Dictionary Representation of Deep Features for Occlusion-Robust Face Recognition

A novel deep dictionary representation-based classification scheme, where a convolutional neural network is employed as the feature extractor and followed by a dictionary to linearly code the extracted deep features, which is robust to large contiguous occlusion.

Generative Image Inpainting with Contextual Attention

This work proposes a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.

Occlusion robust face recognition based on mask learning

Experiments on datasets consisting of real-life and synthetic occluded faces demonstrate that MaskNet can effectively improve the robustness of CNN models towards occlusions in face recognition.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis

This work proposes a multi-scale neural patch synthesis approach based on joint optimization of image content and texture constraints, which not only preserves contextual structures but also produces high-frequency details by matching and adapting patches with the most similar mid-layer feature correlations of a deep classification network.

DeepGender: Occlusion and Low Resolution Robust Facial Gender Classification via Progressively Trained Convolutional Neural Networks with Attention

A progressive convolutional neural network training paradigm is designed to enable the network to attend to particular high-profile regions without the need to change the network architecture itself, and to achieve better gender classification results on the large-scale PCSO mugshot database.

Robust LSTM-Autoencoders for Face De-Occlusion in the Wild.

A robust LSTM-Autoencoders (RLA) model is proposed to effectively restore partially occluded faces even in the wild and provides significantly larger performance gain than other de-occlusion methods in promoting recognition performance over partially-occluded faces.

Context Encoders: Feature Learning by Inpainting

It is found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures, and can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.
...