# Grid Saliency for Context Explanations of Semantic Segmentation

arXiv: https://arxiv.org/abs/1907.13054 · HTML: https://mlsanity.com/paper/1907.13054/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 30 of 32)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation](https://mlsanity.com/paper/2304.13615/) (2023)
- [Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations](https://mlsanity.com/paper/2211.11426/) (2022)
- [Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey](https://mlsanity.com/paper/2405.01636/) (2024)
- [Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better](https://mlsanity.com/paper/2506.12766/) (2025)
- [U-Noise: Learnable Noise Masks for Interpretable Image Segmentation](https://mlsanity.com/paper/2101.05791/) (2021)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2202.03501/) (2022)
- ["Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution](https://mlsanity.com/paper/2209.01782/) (2022)
- [Domain Adaptation based Object Detection for Autonomous Driving in Foggy and Rainy Weather](https://mlsanity.com/paper/2307.09676/) (2023)
- [Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models](https://mlsanity.com/paper/2407.16653/) (2024)
- [Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation](https://mlsanity.com/paper/2409.09497/) (2024)
- [MiSuRe is all you need to explain your image segmentation](https://mlsanity.com/paper/2406.12173/) (2024)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [Outline of an Independent Systematic Blackbox Test for ML-based Systems](https://mlsanity.com/paper/2401.17062/) (2024)
- [MaskAdapt: Unsupervised Geometry-Aware Domain Adaptation Using Multimodal Contextual Learning and RGB-Depth Masking](https://mlsanity.com/paper/2505.24026/) (2025)
- [Adversarially Masked Video Consistency for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.16242/) (2024)
- [Semantic Segmentation on VSPW Dataset through Masked Video Consistency](https://mlsanity.com/paper/2406.04979/) (2024)
- [Leveraging Causal Reasoning Method for Explaining Medical Image Segmentation Models](https://mlsanity.com/paper/2602.20511/) (2026)
- [Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation](https://mlsanity.com/paper/2604.11775/) (2026)

## Abstract (arXiv)

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To overcome this limitation, we extend the existing approaches to generate grid saliencies, which provide spatially coherent visual explanations for (pixel-level) dense prediction networks. As the proposed grid saliency allows to spatially disentangle the object and its context, we specifically explore its potential to produce context explanations for semantic segmentation networks, discovering which context most influences the class predictions inside a target object area. We investigate the effectiveness of grid saliency on a synthetic dataset with an artificially induced bias between objects and their context as well as on the real-world Cityscapes dataset using state-of-the-art segmentation networks. Our results show that grid saliency can be successfully used to provide easily interpretable context explanations and, moreover, can be employed for detecting and localizing contextual biases present in the data.