mlsanityData to 13 Oct 2026

Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models

arXiv 2204.01729 ↗First posted 4 Apr 2022eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced. Training a model on an imbalanced dataset can introduce unique challenges to the learning problem where a model is biased towards the highly frequent class. Many methods are proposed to tackle the distributional differences and the imbalanced problem. However, the impact of these approaches on the learned features is not well studied. In this paper, we look deeper into the internal units of neural networks to observe how handling data imbalance affects the learned features. We study several popular cost-sensitive approaches for handling data imbalance and analyze the feature maps of the convolutional neural networks from multiple perspectives: analyzing the alignment of salient features with pathologies and analyzing the pathology-related concepts encoded by the networks. Our study reveals differences and insights regarding the trained models that are not reflected by quantitative metrics such as AUROC and AP and show up only by looking at the models through a lens.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

27 of 33 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  5. 2016Densely Connected Convolutional Networkscited by 6,707
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,515
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,368
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,434
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,360
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,348
  11. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,243
  12. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 707
15 more
  1. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  2. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 471
  3. 2020Asymmetric Loss For Multi-Label Classificationcited by 379
  4. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 255
  5. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 157
  6. 2019Striking the Right Balance with Uncertaintycited by 79
  7. 2018Review of Visual Saliency Detection with Comprehensive Informationcited by 60
  8. 2021Neural Response Interpretation through the Lens of Critical Pathwayscited by 32
  9. 2022Do Explanations Explain? Model Knows Bestcited by 20
  10. 2021Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Informationcited by 17
  11. 2021Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Featurescited by 9
  12. 2021Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Modelscited by 9
  13. 2019Learning Interpretable Features via Adversarially Robust Optimizationcited by 8
  14. 2019Improving Feature Attribution through Input-specific Network Pruningcited by 7
  15. 2020Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methodscited by 7

Built on by

Not cited yet.