# Deep Feature Augmentation for Occluded Image Classification Source: [Deep Feature Augmentation for Occluded Image Classification]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:42:59.203Z Authors: Feng Cen, Xiaoyu Zhao, Wuzhuang Li, Guanghui Wang (2) \_\_INSTITUTION\_4\_\_ The Department of Control Science & Engineering, College of Electronics, Information Engineering, Tongji University, Shanghai 201804, China, (2) Department of Computer Science, Ryerson University, Toronto, ON, Canada M5B 2K3) Published: 2020-11-02T06:25:05.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()