Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs
Understanding how vision-language models (VLMs) interpret data visualizations remains an open problem, and is increasingly important as these models are used for analytical tasks where reliable reasoning is essential. We introduce a lightweight, diagnostic saliency map method tailored for text generation over images using transformer models, the current state-of-the-art models in visualization interpretation. Our approach aggregates the language model's attention over the visual tokens across all heads and layers, then maps this attention back onto the vision encoder's patch grid to localise it over the image, producing a direct correspondence between each generated answer token and the image regions it attended to. This yields fast, gradient-free saliency maps that expose how VLMs allocate focus across visual elements during answer generation, enabling inspection of whether model attention aligns with semantically relevant components. We evaluate our approach using a deletion metric which validates the causal faithfulness of our saliency maps to the model's behavior.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationText GenerationSimilar Papers 제목 키워드 기반
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention weights. Su…
Natural Language InferenceFree-Lunch Saliency via Attention in Atari Agents
We propose a new approach to visualize saliency maps for deep neural network models and apply it to deep reinforcement learning agents trained on Atari environments. Our method adds an attention module that we call FLS (…
Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehen…
object-detectionObject DetectionSalient Object DetectionSemantic Segmentation+2FuseVis: Interpreting neural networks for image fusion using per-pixel saliency visualization
Image fusion helps in merging two or more images to construct a more informative single fused image. Recently, unsupervised learning based convolutional neural networks (CNN) have been utilized for different types of ima…
Autonomous DrivingMulti-Exposure Image FusionFull-Gradient Representation for Neural Network Visualization
We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed repr…
Interpretable Machine LearningSensitivity