mlsanityData to 7 Oct 2026

Convolutional Dynamic Alignment Networks for Interpretable Classifications

arXiv 2104.00032 ↗First posted 31 Mar 2021cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA-Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which linearly transform their input with weight vectors that dynamically align with task-relevant patterns. As a result, CoDA-Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions. Given the alignment of the DAUs, the resulting contribution maps align with discriminative input patterns. These model-inherent decompositions are of high visual quality and outperform existing attribution methods under quantitative metrics. Further, CoDA-Nets constitute performant classifiers, achieving on par results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

28 of 42 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  9. 2016Wide Residual Networkscited by 3,057
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
16 more
  1. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  2. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  3. 2018Sanity Checks for Saliency Mapscited by 1,149
  4. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  5. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  6. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  7. 2017Dynamic Routing Between Capsulescited by 689
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2014On the Number of Linear Regions of Deep Neural Networkscited by 378
  10. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  11. 2016Dynamic Filter Networkscited by 318
  12. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  13. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  14. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  15. 2017Improved Inception-Residual Convolutional Neural Network for Object Recognitioncited by 5
  16. 2018MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 22; 2024: 10; 2025: 6; 2026: 4.

54 papers.

Sort:

By area:

  1. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  2. 2023Probabilistic Concept Bottleneck Modelscited by 101
  3. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  4. 2022Diffusion Models for Counterfactual Explanationscited by 79
  5. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  6. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  7. 2023Adversarial Counterfactual Visual Explanationscited by 47
  8. 2023B-cos Alignment for Inherently Interpretable CNNs and Vision Transformerscited by 31
  9. 2022Towards Better Understanding Attribution Methodscited by 28
  10. 2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
  11. 2022Interpretable by Design: Learning Predictors by Composing Interpretable Queriescited by 26
  12. 2023Variational Information Pursuit for Interpretable Predictionscited by 25
38 more
  1. 2023PDiscoNet: Semantically consistent part discovery for fine-grained recognitioncited by 21
  2. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  3. 2023Studying How to Efficiently and Effectively Guide Models with Explanationscited by 16
  4. 2023Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?cited by 16
  5. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  6. 2023Explainability of Vision Transformers: A Comprehensive Review and New Perspectivescited by 12
  7. 2024B-cosification: Transforming Deep Neural Networks to be Inherently Interpretablecited by 12
  8. 2022Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attentioncited by 11
  9. 2023Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactualscited by 10
  10. 2023DeViL: Decoding Vision features into Languagecited by 10
  11. 2023A Framework for Interpretability in Machine Learning for Medical Imagingcited by 9
  12. 2023Holistically Explainable Vision Transformerscited by 8
  13. 20233VL: Using Trees to Improve Vision-Language Models' Interpretabilitycited by 7
  14. 2024Benchmarking the Attribution Quality of Vision Modelscited by 7
  15. 2025Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactionscited by 6
  16. 2023Neural Insights for Digital Marketing Content Designcited by 4
  17. 2023Better Understanding Differences in Attribution Methods via Systematic Evaluationscited by 4
  18. 2023From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoringcited by 4
  19. 2025B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainabilitycited by 4
  20. 2025Pixel-level Certified Explanations via Randomized Smoothingcited by 4
  21. 2021A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasetscited by 3
  22. 2023Towards credible visual model interpretation with path attributioncited by 3
  23. 2024Towards Explaining Hypercomplex Neural Networkscited by 3
  24. 2026DAVE: Distribution-aware Attribution via ViT Gradient Decompositioncited by 3
  25. 2023Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretabilitycited by 2
  26. 2021A Comparison of Deep Saliency Map Generators on Multispectral Data in Object Detectioncited by 1
  27. 2021Optimising for Interpretability: Convolutional Dynamic Alignment Networkscited by 1
  28. 2023On Model Explanations with Transferable Neural Pathwayscited by 1
  29. 2024Explainable Transformer Prototypes for Medical Diagnosescited by 1
  30. 2024How Video Meetings Change Your Expressioncited by 1
  31. 2024Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactualscited by 1
  32. 2025Counterfactual Visual Explanation via Causally-Guided Adversarial Steeringcited by 1
  33. 2026Exploring SAIG Methods for an Objective Evaluation of XAIcited by 1
  34. 2026End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attributioncited by 1
  35. 2022A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Conceptscited by 0
  36. 2022Evaluating Feature Attribution Methods for Electrocardiogramcited by 0
  37. 2023Greedy PIG: Adaptive Integrated Gradientscited by 0
  38. 2024Unlearning-based Neural Interpretationscited by 0

50 most cited of 54 All 54 (JSON)