Cover Image

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ying, Rudner, Tim G. J., Wilson, Andrew Gordon
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
by: Gupta, Gunshi, et al.
Published: (2024)

Explanation Bottleneck Models
by: Yamaguchi, Shin'ya, et al.
Published: (2024)

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
by: Zhu, Zhiyu, et al.
Published: (2025)

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
by: Kim, Hongeun, et al.
Published: (2025)

Extending Information Bottleneck Attribution to Video Sequences
by: Solopova, Veronika, et al.
Published: (2025)

Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
by: Feng, Yunzhen, et al.
Published: (2024)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
by: Decker, Thomas, et al.
Published: (2024)

Text-to-Image GAN with Pretrained Representations
by: You, Xiaozhou, et al.
Published: (2024)

Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis
by: Wang, Zhao-Yang, et al.
Published: (2025)

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
by: Li, Zijie, et al.
Published: (2026)

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
by: Hu, Yuanze, et al.
Published: (2025)

Compositional Text-to-Image Generation with Dense Blob Representations
by: Nie, Weili, et al.
Published: (2024)

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
by: Liu, Anjie, et al.
Published: (2026)

M4V: Multi-Modal Mamba for Text-to-Video Generation
by: Huang, Jiancheng, et al.
Published: (2025)

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
by: Nedungadi, Vishal, et al.
Published: (2024)

Text-Guided Multi-Scale Frequency Representation Adaptation
by: Yan, Weicai, et al.
Published: (2026)

The Lie Derivative for Measuring Learned Equivariance
by: Gruver, Nate, et al.
Published: (2022)

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
by: De Santis, Antonio, et al.
Published: (2024)

Fwd2Bot: LVLM Visual Token Compression with Double Forward Bottleneck
by: Bulat, Adrian, et al.
Published: (2025)

Representational Difference Explanations
by: Kondapaneni, Neehar, et al.
Published: (2025)

Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
by: Xu, Kaiwen, et al.
Published: (2023)

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
by: Hong, Jinyung, et al.
Published: (2024)

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
by: Shao, Zedian, et al.
Published: (2026)

When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models
by: Gupta, Hitesh Kumar
Published: (2025)

Multi-Group Proportional Representation for Text-to-Image Models
by: Jung, Sangwon, et al.
Published: (2025)

Attribute-Aware Implicit Modality Alignment for Text Attribute Person Search
by: Wang, Xin, et al.
Published: (2024)

Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction
by: Jian, Yichang, et al.
Published: (2026)

Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection
by: Aggarwal, Sajal, et al.
Published: (2024)

Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization
by: Wall, Casey, et al.
Published: (2025)

Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
by: Doumanoglou, Alexandros, et al.
Published: (2023)

Explainable Visual Anomaly Detection via Concept Bottleneck Models
by: Stropeni, Arianna, et al.
Published: (2025)

VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
by: Munir, Mustafa, et al.
Published: (2025)

MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification
by: Wang, Chunjiang, et al.
Published: (2025)

Attributes-aware Visual Emotion Representation Learning
by: Maharjan, Rahul Singh, et al.
Published: (2025)

Learning Sparse Visual Representations via Spatial-Semantic Factorization
by: Zhao, Theodore Zhengde, et al.
Published: (2026)

Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models
by: Srinivas, Sakhinana Sagar, et al.
Published: (2024)

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
by: Singhi, Nishad, et al.
Published: (2024)

Interpretable Unsupervised Deformable Image Registration via Confidence-bound Multi-Hop Visual Reasoning
by: Iqbal, Zafar, et al.
Published: (2026)

Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifiers
by: Mertes, Silvan, et al.
Published: (2024)

Visual Error Patterns in Multi-Modal AI: A Statistical Approach
by: Wang, Ching-Yi
Published: (2024)