# B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers

arXiv: https://arxiv.org/abs/2306.10898 · HTML: https://mlsanity.com/paper/2306.10898/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 75 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)

## Built on by (most cited first, 30 of 31)

- [Frozen Transformers in Language Models Are Effective Visual Encoder Layers](https://mlsanity.com/paper/2310.12973/) (2023)
- [A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models](https://mlsanity.com/paper/2404.14955/) (2024)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Good Teachers Explain: Explanation-Enhanced Knowledge Distillation](https://mlsanity.com/paper/2402.03119/) (2024)
- [B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable](https://mlsanity.com/paper/2411.00715/) (2024)
- [CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification](https://mlsanity.com/paper/2503.15234/) (2025)
- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations](https://mlsanity.com/paper/2406.05068/) (2024)
- [Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions](https://mlsanity.com/paper/2508.05430/) (2025)
- [B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability](https://mlsanity.com/paper/2502.12992/) (2025)
- [DAVE: Distribution-aware Attribution via ViT Gradient Decomposition](https://mlsanity.com/paper/2602.06613/) (2026)
- [Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning](https://mlsanity.com/paper/2503.08636/) (2025)
- [OMENN: One Matrix to Explain Neural Networks](https://mlsanity.com/paper/2412.02399/) (2024)
- [From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection](https://mlsanity.com/paper/2505.06003/) (2025)
- [Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2406.05477/) (2024)
- [COMIX: Compositional Explanations using Prototypes](https://mlsanity.com/paper/2501.06059/) (2025)
- [Disentangling Visual Transformers: Patch-level Interpretability for Image Classification](https://mlsanity.com/paper/2502.17196/) (2025)
- [FaCT: Faithful Concept Traces for Explaining Neural Network Decisions](https://mlsanity.com/paper/2510.25512/) (2025)
- [Exploring SAIG Methods for an Objective Evaluation of XAI](https://mlsanity.com/paper/2602.08715/) (2026)
- [End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution](https://mlsanity.com/paper/2603.25798/) (2026)
- [IMAFD: An Interpretable Multi-stage Approach to Flood Detection from time series Multispectral Data](https://mlsanity.com/paper/2405.07916/) (2024)
- [SIC: Similarity-Based Interpretable Image Classification with Neural Networks](https://mlsanity.com/paper/2501.17328/) (2025)
- [PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis](https://mlsanity.com/paper/2506.10669/) (2025)
- [Interpretable Diffusion Models with B-cos Networks](https://mlsanity.com/paper/2507.03846/) (2025)
- [Pulling Back the Curtain on Deep Networks](https://mlsanity.com/paper/2507.22832/) (2025)
- [DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification](https://mlsanity.com/paper/2604.07166/) (2026)
- [When Can We Trust Deep Neural Networks? Towards Reliable Industrial Deployment with an Interpretability Guide](https://mlsanity.com/paper/2604.19206/) (2026)
- [B-cos GNNs: Faithful Explanations through Dynamic Linearity](https://mlsanity.com/paper/2605.19778/) (2026)
- [GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis](https://mlsanity.com/paper/2606.30901/) (2026)

## Abstract (arXiv)

We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace the linear transformations in DNNs by our novel B-cos transformation. As we show, a sequence (network) of such transformations induces a single linear transformation that faithfully summarises the full model computations. Moreover, the B-cos transformation is designed such that the weights align with relevant signals during optimisation. As a result, those induced linear transformations become highly interpretable and highlight task-relevant features. Importantly, the B-cos transformation is designed to be compatible with existing architectures and we show that it can easily be integrated into virtually all of the latest state of the art models for computer vision - e.g. ResNets, DenseNets, ConvNext models, as well as Vision Transformers - by combining the B-cos-based explanations with normalisation and attention layers, all whilst maintaining similar accuracy on ImageNet. Finally, we show that the resulting explanations are of high visual quality and perform well under quantitative interpretability metrics.