mlsanityData to 14 Oct 2026

Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks

arXiv 2306.07724 ↗First posted 13 Jun 2023cs.CV cs.LG eess.IVcited by 1

Not on the map. Why?

Abstract (arXiv)

Images cannot always be expected to come in a certain standard format and orientation. Deep networks need to be trained to take into account unexpected variations in orientation or format. For this purpose, training data should be enriched to include different conditions. In this study, the effects of data enrichment on the performance of deep networks in the super resolution problem were investigated experimentally. A total of six basic image transformations were used for the enrichment procedures. In the experiments, two deep network models were trained with variants of the ILSVRC2012 dataset enriched by these six image transformation processes. Considering a single image transformation, it has been observed that the data enriched with 180 degree rotation provides the best results. The most unsuccessful result was obtained when the models were trained on the enriched data generated by the flip upside down process. Models scored highest when trained with a mix of all transformations.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

18 of 42 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  5. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  7. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  10. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  11. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  12. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
6 more
  1. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  2. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  3. 2019Image Super-Resolution by Neural Texture Transfercited by 120
  4. 2017Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Networkcited by 17
  5. 2019Generative Collaborative Networks for Single Image Super-Resolutioncited by 2
  6. 2017Learning Image Relations with Contrast Association Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Transformation Behavior of Images in Latent Spacecited by 0