mlsanityData to 7 Oct 2026

EscherNet 101

arXiv 2303.04208 ↗First posted 7 Mar 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A deep learning model, EscherNet 101, is constructed to categorize images of 2D periodic patterns into their respective 17 wallpaper groups. Beyond evaluating EscherNet 101 performance by classification rates, at a micro-level we investigate the filters learned at different layers in the network, capable of capturing second-order invariants beyond edge and curvature.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 62 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

20 of 62 references.

References · 20

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2016Group Equivariant Convolutional Networkscited by 1,154
  7. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  8. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  9. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  10. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  11. 2016Steerable CNNscited by 298
  12. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
8 more
  1. 2016The THUMOS Challenge on Action Recognition for Videos "in the Wild"cited by 213
  2. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  3. 2016Grad-CAM: Why did you say that?cited by 159
  4. 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
  5. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  6. 2014Analyzing the Performance of Multilayer Neural Networks for Object Recognitioncited by 29
  7. 2017Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wildcited by 17
  8. 2016Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputscited by 9

Built on by

Not cited yet.