Papers › Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training...

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

11 Apr 2017arXiv:1704.03557archive 2025-07-28

Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDocClassifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a huge set of document images, i.e. 400,000 documents. Third, it analyzes the impact of the amount of training data (document images) and other parameters to the classification abilities. We use two datasets, the Tobacco-3482 and the large-scale RVL-CDIP dataset. We achieve an accuracy of 91.13% for the Tobacco-3482 dataset while earlier approaches reach only 77.6%. Thus, a relative error reduction of more than 60% is achieved. For the large dataset RVL-CDIP, an accuracy of 90.97% is achieved, corresponding to a relative error reduction of 11.5%.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

BordiaS/layoutlm mentioned on GitHubpytorch report
microsoft/unilm mentioned on GitHubpytorch report
tuannamnguyen93/DFKI_test_PhD mentioned on GitHubtf report
tuannamnguyen93/test_PhD mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document Image ClassificationGeneral ClassificationImage ClassificationObject RecognitionTransfer Learningdocument-image-classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Image Classification RVL-CDIP Transfer Learning from AlexNet, VGG-16, GoogLeNet and ResNet50 Accuracy 90.97% #28 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections