# CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency

arXiv: https://arxiv.org/abs/2106.10649 · HTML: https://mlsanity.com/paper/2106.10649/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 20 Jun 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [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)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Visualizing Deep Neural Network Decisions: Prediction Difference Analysis](https://mlsanity.com/paper/1702.04595/) (2017)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [There and Back Again: Revisiting Backpropagation Saliency Methods](https://mlsanity.com/paper/2004.02866/) (2020)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)

## Built on by (most cited first, 28 of 28)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries](https://mlsanity.com/paper/2302.12828/) (2023)
- [Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity](https://mlsanity.com/paper/2107.07013/) (2021)
- [FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs](https://mlsanity.com/paper/2206.08792/) (2022)
- [Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector](https://mlsanity.com/paper/2407.19308/) (2024)
- [A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics](https://mlsanity.com/paper/2301.13445/) (2023)
- [DRG-Net: Interactive Joint Learning of Multi-lesion Segmentation and Classification for Diabetic Retinopathy Grading](https://mlsanity.com/paper/2212.14615/) (2022)
- [Towards credible visual model interpretation with path attribution](https://mlsanity.com/paper/2305.14395/) (2023)
- [Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers](https://mlsanity.com/paper/2303.17836/) (2023)
- [MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations](https://mlsanity.com/paper/2602.18792/) (2026)
- [Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation](https://mlsanity.com/paper/2606.22901/) (2026)
- [Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance](https://mlsanity.com/paper/2312.14201/) (2023)
- [Generating visual explanations from deep networks using implicit neural representations](https://mlsanity.com/paper/2501.11784/) (2025)
- [Disentangling Visual Transformers: Patch-level Interpretability for Image Classification](https://mlsanity.com/paper/2502.17196/) (2025)
- [Counterfactual Visual Explanation via Causally-Guided Adversarial Steering](https://mlsanity.com/paper/2507.09881/) (2025)
- [A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts](https://mlsanity.com/paper/2201.07798/) (2022)
- [Rethinking gradient weights' influence over saliency map estimation](https://mlsanity.com/paper/2207.05374/) (2022)
- [TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts](https://mlsanity.com/paper/2210.03274/) (2022)
- [Decoupling Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/2210.08336/) (2022)
- [An Experimental Investigation into the Evaluation of Explainability Methods](https://mlsanity.com/paper/2305.16361/) (2023)
- [Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map](https://mlsanity.com/paper/2306.04644/) (2023)
- [On Transfer-based Universal Attacks in Pure Black-box Setting](https://mlsanity.com/paper/2504.08866/) (2025)
- [Do Protein Transformers Have Biological Intelligence?](https://mlsanity.com/paper/2506.06701/) (2025)
- [CASE: Contrastive Activation for Class-Sensitive Explanations](https://mlsanity.com/paper/2506.07327/) (2025)
- [Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty](https://mlsanity.com/paper/2506.19442/) (2025)
- [Attribution Upsampling should Redistribute, Not Interpolate](https://mlsanity.com/paper/2603.16067/) (2026)

## Abstract (arXiv)

Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the earlier layers in a network only allows saliency computation with low resolution activation maps of the deeper layers, resulting in compromised image saliency. Remedifying this can lead to sanity failures. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors and preserving the map sanity. Our method systematically performs multi-scale accumulation and fusion of the activation maps and backpropagated gradients to compute precise saliency maps. From accurate image saliency to articulation of relative importance of input features for different models, and precise discrimination between model perception of visually similar objects, our high-resolution mapping offers multiple novel insights into the black-box deep visual models, which are presented in the paper. We also demonstrate the utility of our saliency maps in adversarial setup by drastically reducing the norm of attack signals by focusing them on the precise regions identified by our maps. Our method also inspires new evaluation metrics and a sanity check for this developing research direction. Code is available here https://github.com/VisMIL/CAMERAS