mlsanityData to 7 Oct 2026

Improving filling level classification with adversarial training

arXiv 2102.04057 ↗First posted 8 Feb 2021cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. This problem is made challenging by several ambiguities caused by transparencies, shape variations and partial occlusions, and by the availability of only small training datasets. In this paper, we tackle this problem with an appropriate strategy for transfer learning. Specifically, we use adversarial training in a generic source dataset and then refine the training with a task-specific dataset. We also discuss and experimentally evaluate several training strategies and their combination on a range of container types of the CORSMAL Containers Manipulation dataset. We show that transfer learning with adversarial training in the source domain consistently improves the classification accuracy on the test set and limits the overfitting of the classifier to specific features of the training data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

22 of 32 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Mask R-CNNcited by 7,259
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Wide Residual Networkscited by 3,057
  8. 2014How transferable are features in deep neural networks?cited by 1,216
  9. 2018Robustness May Be at Odds with Accuracycited by 873
  10. 2018Do Better ImageNet Models Transfer Better?cited by 560
  11. 2018A Survey on Deep Transfer Learningcited by 417
  12. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
10 more
  1. 2016What makes ImageNet good for transfer learning?cited by 192
  2. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  3. 2020Feature Purification: How Adversarial Training Performs Robust Deep Learningcited by 107
  4. 2018Deep Texture Manifold for Ground Terrain Recognitioncited by 32
  5. 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
  6. 2016Visual Closed-Loop Control for Pouring Liquidscited by 26
  7. 2020Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classificationcited by 18
  8. 2017See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Contentcited by 11
  9. 2018Accurate Pouring with an Autonomous Robot Using an RGB-D Cameracited by 8
  10. 2017Reasoning About Liquids via Closed-Loop Simulationcited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 0; 2024: 0; 2025: 1.

5 papers.

  1. 2021The CORSMAL benchmark for the prediction of the properties of containerscited by 6
  2. 2022Container Localisation and Mass Estimation with an RGB-D Cameracited by 2
  3. 2022Audio-Visual Object Classification for Human-Robot Collaborationcited by 2
  4. 2025Learning Privacy from Visual Entitiescited by 2
  5. 2022Data augmentation with mixtures of max-entropy transformations for filling-level classificationcited by 1