mlsanityData to 7 Oct 2026

Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets

arXiv 2206.09697 ↗First posted 20 Jun 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for the last layer. This idea comes from transfer learning, which uses networks pre-trained on other data and extracts different levels of the network as input for the new task. The second improvement is the use of deeper layers instead of deeper sequences of blocks. This idea comes from Wide ResNets. Using both optimizations, both high data augmentation and standard data augmentation can produce better results for different models. Link: https://github.com/wolfgangfuhl/PublicationStuff/tree/master/TechnicalReport1/Supp

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

24 of 50 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Wide Residual Networkscited by 3,057
  3. 2019Fast AutoAugmentcited by 243
  4. 2021TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Typescited by 32
  5. 2016PupilNet: Convolutional Neural Networks for Robust Pupil Detectioncited by 20
  6. 2015ElSe: Ellipse Selection for Robust Pupil Detection in Real-World Environmentscited by 16
  7. 2020Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and Reconstructioncited by 12
  8. 2020Rotated Ring, Radial and Depth Wise Separable Radial Convolutionscited by 12
  9. 2018Eye movement velocity and gaze data generator for evaluation, robustness testing and assess of eye tracking software and visualization toolscited by 11
  10. 2019Learning to Validate the Quality of Detected Landmarkscited by 11
  11. 2020Weight and Gradient Centralization in Deep Neural Networkscited by 11
  12. 2017Fast camera focus estimation for gaze-based focus controlcited by 10
12 more
  1. 2018Eye movement simulation and detector creation to reduce laborious parameter adjustmentscited by 10
  2. 2019Training Decision Trees as Replacement for Convolution Layerscited by 10
  3. 2021The Gaze and Mouse Signal as additional Source for User Fingerprints in Browser Applicationscited by 10
  4. 2022Pistol: Pupil Invisible Supportive Tool to extract Pupil, Iris, Eye Opening, Eye Movements, Pupil and Iris Gaze Vector, and 2D as well as 3D Gazecited by 9
  5. 2020Multi Layer Neural Networks as Replacement for Pooling Operationscited by 8
  6. 2020Explainable Online Validation of Machine Learning Models for Practical Applicationscited by 8
  7. 2021A Multimodal Eye Movement Dataset and a Multimodal Eye Movement Segmentation Analysiscited by 7
  8. 20211000 Pupil Segmentations in a Second using Haar Like Features and Statistical Learningcited by 7
  9. 2022HPCGen: Hierarchical K-Means Clustering and Level Based Principal Components for Scan Path Genarationcited by 5
  10. 2021Maximum and Leaky Maximum Propagationcited by 4
  11. 2021Tensor Normalization and Full Distribution Trainingcited by 3
  12. 2022GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projectioncited by 2

Built on by

Not cited yet.