# Real Time Image Saliency for Black Box Classifiers

arXiv: https://arxiv.org/abs/1705.07857 · HTML: https://mlsanity.com/paper/1705.07857/

## Key facts

- Cited by 246 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2017.

## Built on by (most cited first, 30 of 246)

- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets](https://mlsanity.com/paper/2103.12028/) (2021)
- [IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers](https://mlsanity.com/paper/2106.12620/) (2021)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [PlanT: Explainable Planning Transformers via Object-Level Representations](https://mlsanity.com/paper/2210.14222/) (2022)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations](https://mlsanity.com/paper/2206.01254/) (2022)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations](https://mlsanity.com/paper/2103.01890/) (2021)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games](https://mlsanity.com/paper/2201.12380/) (2022)
- [Optimizing Relevance Maps of Vision Transformers Improves Robustness](https://mlsanity.com/paper/2206.01161/) (2022)
- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning](https://mlsanity.com/paper/2101.12446/) (2021)
- [Model Zoos: A Dataset of Diverse Populations of Neural Network Models](https://mlsanity.com/paper/2209.14764/) (2022)
- [Missingness Bias in Model Debugging](https://mlsanity.com/paper/2204.08945/) (2022)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/2103.13859/) (2021)
- [Defining and Quantifying the Emergence of Sparse Concepts in DNNs](https://mlsanity.com/paper/2111.06206/) (2021)
- [Locally Sparse Neural Networks for Tabular Biomedical Data](https://mlsanity.com/paper/2106.06468/) (2021)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals](https://mlsanity.com/paper/2203.12892/) (2022)
- [ModelDiff: A Framework for Comparing Learning Algorithms](https://mlsanity.com/paper/2211.12491/) (2022)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)

## Abstract (arXiv)

In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model generalises well to unseen images and requires a single forward pass to perform saliency detection, therefore suitable for use in real-time systems. We test our approach on CIFAR-10 and ImageNet datasets and show that the produced saliency maps are easily interpretable, sharp, and free of artifacts. We suggest a new metric for saliency and test our method on the ImageNet object localisation task. We achieve results outperforming other weakly supervised methods.