# Explainable Deep Classification Models for Domain Generalization

arXiv: https://arxiv.org/abs/2003.06498 · HTML: https://mlsanity.com/paper/2003.06498/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

## Built on by (most cited first, 27 of 27)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Learning Support and Trivial Prototypes for Interpretable Image Classification](https://mlsanity.com/paper/2301.04011/) (2023)
- [Attention Consistency on Visual Corruptions for Single-Source Domain Generalization](https://mlsanity.com/paper/2204.13091/) (2022)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Variational Disentanglement for Domain Generalization](https://mlsanity.com/paper/2109.05826/) (2021)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning](https://mlsanity.com/paper/2306.04641/) (2023)
- [XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach](https://mlsanity.com/paper/2407.11771/) (2024)
- [Explainable Misinformation Detection Across Multiple Social Media Platforms](https://mlsanity.com/paper/2203.11724/) (2022)
- [Fine-Grained Visual Entailment](https://mlsanity.com/paper/2203.15704/) (2022)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [Explaining Cross-Domain Recognition with Interpretable Deep Classifier](https://mlsanity.com/paper/2211.08249/) (2022)
- [Improving Network Interpretability via Explanation Consistency Evaluation](https://mlsanity.com/paper/2408.04600/) (2024)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation](https://mlsanity.com/paper/2109.05742/) (2021)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2505.19659/) (2025)
- [Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection](https://mlsanity.com/paper/2209.08681/) (2022)
- [Fairness via Adversarial Attribute Neighbourhood Robust Learning](https://mlsanity.com/paper/2210.06630/) (2022)
- [Relevance-guided Neural Machine Translation](https://mlsanity.com/paper/2312.00214/) (2023)
- [GroupMixNorm Layer for Learning Fair Models](https://mlsanity.com/paper/2312.11969/) (2023)
- [IMPACTX: improving model performance by appropriately constraining the training with teacher explanations](https://mlsanity.com/paper/2502.12222/) (2025)

## Abstract (arXiv)

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network's decision. Our training strategy enforces a periodic saliency-based feedback to encourage the model to focus on the image regions that directly correspond to the ground-truth object. We quantify explainability using an automated metric, and using human judgement. We propose explainability as a means for bridging the visual-semantic gap between different domains where model explanations are used as a means of disentagling domain specific information from otherwise relevant features. We demonstrate that this leads to improved generalization to new domains without hindering performance on the original domain.