It has been observed that visual classification models often rely mostly on spurious cues such as the image background, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the model's relevancy signal and direct the model to base its prediction on the foregroundobject.

Explainable AI (XAI) methods help identify which image regions influence a model's prediction, but often face a trade-off between detail and interpretability. Layer-wise Relevance Propagation (LRP) offers a model-aware alternative. However, LRP implementations commonly rely on heuristic rule sets that are not optimized for clarity or alignment with model behavior. We introduce EVO-LRP, a method that applies Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to tune LRP hyperparameters based on quantitative interpretability metrics, such as faithfulness or sparseness. EVO-LRP outperforms traditional XAI approaches in both interpretability metric performance and visual coherence, with strong sensitivity to class-specific features. These findings demonstrate that attribution quality can be systematically improved through principled, task-specific optimization.

It has been observed that visual classification models often rely mostly on spurious cues such as the image background, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the model's relevancy signal and direct the model to base its prediction on the foreground object.

We propose DocVXQA, a novel framework for visually self-explainable document question answering. The framework is designed not only to produce accurate answers to questions but also to learn visual heatmaps that highlight contextually critical regions, thereby offering interpretable justifications for the model's decisions. To integrate explanations into the learning process, we quantitatively formulate explainability principles as explicit learning objectives. Unlike conventional methods that emphasize only the regions pertinent to the answer, our framework delivers explanations that are \textit{contextually sufficient} while remaining \textit{representation-efficient}. This fosters user trust while achieving a balance between predictive performance and interpretability in DocVQA applications. Extensive experiments, including human evaluation, provide strong evidence supporting the effectiveness of our method. The code is available at https://github.com/dali92002/DocVXQA.

Extreme weather events are increasing in frequency and intensity due to climate change. This, in turn, is exacting a significant toll in communities worldwide. While prediction skills are increasing with advances in numerical weather prediction and artificial intelligence tools, extreme weather still present challenges. More specifically, identifying the precursors of such extreme weather events and how these precursors may evolve under climate change remain unclear. In this paper, we propose to use post-hoc interpretability methods to construct relevance weather maps that show the key extreme-weather precursors identified by deep learning models. We then compare this machine view with existing domain knowledge to understand whether deep learning models identified patterns in data that may enrich our understanding of extreme-weather precursors. We finally bin these relevant maps into different multi-year time periods to understand the role that climate change is having on these precursors. The experiments are carried out on Indochina heatwaves, but the methodology can be readily extended to other extreme weather events worldwide.

We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA framework addresses the need for explainability in temporal models used for video analysis. To demonstrate its effectiveness, we apply VIBA to video deepfake detection, testing it on two architectures: the Xception model for spatial features and a VGG11-based model for capturing motion dynamics through optical flow. Using a custom dataset that reflects recent deepfake generation techniques, we adapt IBA to create relevance and optical flow maps, visually highlighting manipulated regions and motion inconsistencies. Our results show that VIBA generates temporally and spatially consistent explanations, which align closely with human annotations, thus providing interpretability for video classification and particularly for deepfake detection.

Transformers have revolutionized Computer Vision (CV) and Natural Language Processing (NLP) through self-attention mechanisms. However, due to their complexity, their latent token representations are often difficult to interpret. We introduce a novel framework that interprets Transformer embeddings, uncovering meaningful semantic patterns within them. Based on this framework, we demonstrate that zero-shot unsupervised semantic segmentation can be performed effectively without any fine-tuning using a model pre-trained for tasks other than segmentation. Our method reveals the inherent capacity of Transformer models for understanding input semantics and achieves state-of-the-art performance in semantic segmentation, outperforming traditional segmentation models. Specifically, our approach achieves an accuracy of 67.2 % and an mIoU of 32.9 % on the COCO-Stuff dataset, as well as an mIoU of 51.9 % on the PASCAL VOC dataset. Additionally, we validate our interpretability framework on LLMs for text summarization, demonstrating its broad applicability and robustness.

Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech models to the applications of Automatic Speech Assessment. One question that has not been explored is how these models output the results based on their inputs. In this work, we train and compare two configurations of Audio Spectrogram Transformer in the context of Voice Disorder Detection and apply the attention rollout method to produce model relevance maps, the computed relevance of the spectrogram regions when the model makes predictions. We use these maps to analyse how models make predictions in different conditions and to show that the spread of attention is reduced as a model is finetuned, and the model attention is concentrated on specific phoneme regions.

The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. We tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. Our findings reveal that ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across games. Finally, we noted that the agent's attention to its paddle emerged relatively late in the training and coincided with a marked increase in its performance score. Overall, we believe that ATOMs could significantly enhance our understanding of RL agents' learning processes, which is essential for improving their reliability and efficiency.