mlsanityData to 14 Oct 2026

On Pitfalls of Measuring Occlusion Robustness through Data Distortion

arXiv 2211.13734 ↗First posted 24 Nov 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Over the past years, the crucial role of data has largely been shadowed by the field's focus on architectures and training procedures. We often cause changes to the data without being aware of their wider implications. In this paper we show that distorting images without accounting for the artefacts introduced leads to biased results when establishing occlusion robustness. To ensure models behave as expected in real-world scenarios, we need to rule out the impact added artefacts have on evaluation. We propose a new approach, iOcclusion, as a fairer alternative for applications where the possible occluders are unknown.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 24 Nov 2022.

Builds on

18 of 21 references.

References · 18

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  10. 2017Random Erasing Data Augmentationcited by 1,239
  11. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  12. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
6 more
  1. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  2. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 142
  3. 2020Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusioncited by 38
  4. 2020An Empirical Evaluation on Robustness and Uncertainty of Regularization Methodscited by 28
  5. 2019Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Modelscited by 18
  6. 2020FMix: Enhancing Mixed Sample Data Augmentationcited by 11

Built on by

Not cited yet.