mlsanityData to 7 Oct 2026

Regression Concept Vectors for Bidirectional Explanations in Histopathology

arXiv 1904.04520 ↗First posted 9 Apr 2019cs.LG cs.CV stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in the activation space of a layer. The directional derivative of the decision function along the RCVs represents the network sensitivity to increasing values of a given concept measure. When applied to breast cancer grading, nuclei texture emerges as a relevant concept in the detection of tumor tissue in breast lymph node samples. We evaluate score robustness and consistency by statistical analysis.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 7; 2024: 3; 2025: 7; 2026: 2.

31 papers.

Sort:

By area:

  1. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  2. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  3. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  4. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  5. 2023Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosiscited by 26
  6. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  7. 2021Best of both worlds: local and global explanations with human-understandable conceptscited by 22
  8. 2022Concept Embedding Analysis: A Reviewcited by 20
  9. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
  10. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  11. 2021FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imagingcited by 13
  12. 2023Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainabilitycited by 11
19 more
  1. 2024Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classificationcited by 11
  2. 2021Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Toolscited by 9
  3. 2025Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathologycited by 8
  4. 2023Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spacescited by 7
  5. 2022Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Informationcited by 6
  6. 2023Uncovering Unique Concept Vectors through Latent Space Decompositioncited by 5
  7. 2025FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networkscited by 5
  8. 2021Neural-Symbolic Integration for Interactive Learning and Conceptual Groundingcited by 3
  9. 2023Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifierscited by 3
  10. 2023Scalable Concept Extraction in Industry 4.0cited by 2
  11. 2024Concept-based Explainable Malignancy Scoring on Pulmonary Nodules in CT Imagescited by 2
  12. 2025In-hoc Concept Representations to Regularise Deep Learning in Medical Imagingcited by 2
  13. 2025On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNscited by 1
  14. 2025Concept-Based Interpretability for Toxicity Detectioncited by 1
  15. 2022LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networkscited by 0
  16. 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinementcited by 0
  17. 2025Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based propertiescited by 0
  18. 2026MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Spacecited by 0
  19. 2026ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using conceptscited by 0