mlsanityData to 7 Oct 2026

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

arXiv 2301.07407 ↗First posted 18 Jan 2023cs.CVcited by 6

Not on the map. Why?

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

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 18 Jan 2023.

Builds on

19 of 29 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  7. 2018Sanity Checks for Saliency Mapscited by 1,149
  8. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  10. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  11. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  12. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
7 more
  1. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 223
  2. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  3. 2018Attention Branch Network: Learning of Attention Mechanism for Visual Explanationcited by 108
  4. 2018Learn To Pay Attentioncited by 83
  5. 2020Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregationcited by 13
  6. 2021Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networkscited by 11
  7. 2022Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanismcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 2.

6 papers.

  1. 2023Explain Any Concept: Segment Anything Meets Concept-Based Explanationcited by 37
  2. 2025Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorizationcited by 10
  3. 2024T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformerscited by 4
  4. 2023On The Coherence of Quantitative Evaluation of Visual Explanationscited by 1
  5. 2024Deep spatial context: when attention-based models meet spatial regressioncited by 1
  6. 2025P-TAME: Explain Any Image Classifier with Trained Perturbationscited by 0