# Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2102.07799 · HTML: https://mlsanity.com/paper/2102.07799/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 13 of 13)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [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)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [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)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation](https://mlsanity.com/paper/2010.00672/) (2020)

## Built on by (most cited first, 11 of 11)

- [Towards Better Explanations for Object Detection](https://mlsanity.com/paper/2306.02744/) (2023)
- [LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks](https://mlsanity.com/paper/2402.12525/) (2024)
- [Towards Trust of Explainable AI in Thyroid Nodule Diagnosis](https://mlsanity.com/paper/2303.04731/) (2023)
- [Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism](https://mlsanity.com/paper/2209.11189/) (2022)
- [TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks](https://mlsanity.com/paper/2301.07407/) (2023)
- [ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network](https://mlsanity.com/paper/2207.09927/) (2022)
- [T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers](https://mlsanity.com/paper/2403.04523/) (2024)
- [Context Attribution with Multi-Armed Bandit Optimization](https://mlsanity.com/paper/2506.19977/) (2025)
- [On The Coherence of Quantitative Evaluation of Visual Explanations](https://mlsanity.com/paper/2302.10764/) (2023)
- [Rethinking gradient weights' influence over saliency map estimation](https://mlsanity.com/paper/2207.05374/) (2022)
- [P-TAME: Explain Any Image Classifier with Trained Perturbations](https://mlsanity.com/paper/2501.17813/) (2025)

## Abstract (arXiv)

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but backpropagation techniques are still prevailing because of their computational efficiency. In this work, we combine both approaches as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks. Our method adaptively selects the most critical features that mainly contribute towards a prediction to probe the model by finding the activated features. Experimental results show that the proposed method can reduce the execution time up to 30% while enhancing competitive interpretability without compromising the quality of explanation generated.