# TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2301.07407 · HTML: https://mlsanity.com/paper/2301.07407/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 18 Jan 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://mlsanity.com/paper/1803.09820/) (2018)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [Learn To Pay Attention](https://mlsanity.com/paper/1804.02391/) (2018)
- [Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation](https://mlsanity.com/paper/2010.00672/) (2020)
- [Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks](https://mlsanity.com/paper/2102.07799/) (2021)
- [Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism](https://mlsanity.com/paper/2209.11189/) (2022)

## Built on by (most cited first, 6 of 6)

- [Explain Any Concept: Segment Anything Meets Concept-Based Explanation](https://mlsanity.com/paper/2305.10289/) (2023)
- [Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization](https://mlsanity.com/paper/2507.10846/) (2025)
- [T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers](https://mlsanity.com/paper/2403.04523/) (2024)
- [On The Coherence of Quantitative Evaluation of Visual Explanations](https://mlsanity.com/paper/2302.10764/) (2023)
- [Deep spatial context: when attention-based models meet spatial regression](https://mlsanity.com/paper/2401.10044/) (2024)
- [P-TAME: Explain Any Image Classifier with Trained Perturbations](https://mlsanity.com/paper/2501.17813/) (2025)

## Abstract (arXiv)

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation maps with a multi-branch hierarchical attention mechanism. TAME combines a target model's feature maps from multiple layers using an attention mechanism, transforming them into an explanation map. TAME can easily be applied to any convolutional neural network (CNN) by streamlining the optimization of the attention mechanism's training method and the selection of target model's feature maps. After training, explanation maps can be computed in a single forward pass. We apply TAME to two widely used models, i.e. VGG-16 and ResNet-50, trained on ImageNet and show improvements over previous top-performing methods. We also provide a comprehensive ablation study comparing the performance of different variations of TAME's architecture. TAME source code is made publicly available at https://github.com/bmezaris/TAME