mlsanityData to 7 Oct 2026

Improving the trustworthiness of image classification models by utilizing bounding-box annotations

arXiv 2108.10131 ↗First posted 15 Aug 2021cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates bounding box information, which is available in many image classification datasets. Preliminary experimental results show that the proposed algorithm achieves better performance in accuracy, robustness, and interpretability compared with baselines.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 15 Aug 2021.

Builds on

21 of 35 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2018Robustness May Be at Odds with Accuracycited by 873
  9. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  10. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  11. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  12. 2015Unifying distillation and privileged informationcited by 218
9 more
  1. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  2. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 107
  3. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  4. 2018Hierarchical interpretations for neural network predictionscited by 66
  5. 2016Rationale-Augmented Convolutional Neural Networks for Text Classificationcited by 39
  6. 2019Embedding Human Knowledge into Deep Neural Network via Attention Mapcited by 33
  7. 2018Deep Learning under Privileged Information Using Heteroscedastic Dropoutcited by 26
  8. 2019Bridging Adversarial Robustness and Gradient Interpretabilitycited by 22
  9. 2019An Empirical Study on the Relation between Network Interpretability and Adversarial Robustnesscited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 0; 2025: 1.

4 papers.

  1. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  2. 2025Large Language Models as Attribution Regularizers for Efficient Model Trainingcited by 1
  3. 2021SIM-ECG: A Signal Importance Mask-driven ECGClassification Systemcited by 0
  4. 2022Towards Better Guided Attention and Human Knowledge Insertion in Deep Convolutional Neural Networkscited by 0