mlsanityData to 7 Oct 2026

ECLAD: Extracting Concepts with Local Aggregated Descriptors

arXiv 2206.04531 ↗First posted 9 Jun 2022cs.CV cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level explanations of the prediction process of CNNs through concept extraction. While these methods can detect whether or not a concept is present in an image, they are unable to determine its location. What is more, a fair comparison of such approaches is difficult due to a lack of proper validation procedures. To address these issues, we propose a novel method for automatic concept extraction and localization based on representations obtained through pixel-wise aggregations of CNN activation maps. Further, we introduce a process for the validation of concept-extraction techniques based on synthetic datasets with pixel-wise annotations of their main components, reducing the need for human intervention. Extensive experimentation on both synthetic and real-world datasets demonstrates that our method outperforms state-of-the-art alternatives.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

29 of 47 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  10. 2018Sanity Checks for Saliency Mapscited by 1,149
  11. 2020Concept Bottleneck Modelscited by 1,022
  12. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
17 more
  1. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  2. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  3. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  4. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  5. 2019Explainable Machine Learning in Deploymentcited by 210
  6. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  7. 2020Explainable deep learning models in medical image analysiscited by 111
  8. 2019Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruningcited by 89
  9. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  10. 2019Visualizing Deep Networks by Optimizing with Integrated Gradientscited by 59
  11. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  12. 2021A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Conceptscited by 33
  13. 2021Best of both worlds: local and global explanations with human-understandable conceptscited by 22
  14. 2020Explaining Deep Neural Networks using Unsupervised Clusteringcited by 9
  15. 2021Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanationcited by 8
  16. 2020Abstracting Deep Neural Networks into Concept Graphs for Concept Level Interpretabilitycited by 6
  17. 2021Failing Conceptually: Concept-Based Explanations of Dataset Shiftcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 4; 2025: 4; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Learning Bottleneck Concepts in Image Classificationcited by 49
  2. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  3. 2023Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spacescited by 7
  4. 2022Automatic Infectious Disease Classification Analysis with Concept Discoverycited by 2
  5. 2023Scalable Concept Extraction in Industry 4.0cited by 2
  6. 2023SurroCBM: Concept Bottleneck Surrogate Models for Generative Post-hoc Explanationcited by 2
  7. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  8. 2024Unveiling Ontological Commitment in Multi-Modal Foundation Modelscited by 1
  9. 2025Multi-level Neural Networks for high-dimensional parametric obstacle problemscited by 1
  10. 2025On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNscited by 1
  11. 2025CE-FAM: Concept-Based Explanation via Fusion of Activation Mapscited by 1
  12. 2024The Anatomy of Adversarial Attacks: Concept-based XAI Dissectioncited by 0
3 more
  1. 2024PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyondcited by 0
  2. 2026Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddingscited by 0
  3. 2026CENDRe: Concept Extraction with Natural Domain Representationscited by 0