Cover Image

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Jung-Ho, Kim, Ho-Joong, Jeon, Kyu-Sung, Lee, Seong-Whan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
by: Kim, Ho-Joong, et al.
Published: (2025)

Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance
by: Hong, Jung-Ho, et al.
Published: (2023)

TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
by: Kim, Ho-Joong, et al.
Published: (2024)

ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
by: Kim, Ji-Hyeon, et al.
Published: (2026)

FIQ: Fundamental Question Generation with the Integration of Question Embeddings for Video Question Answering
by: Oh, Ju-Young, et al.
Published: (2025)

MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval
by: Ju, Yeong-Joon, et al.
Published: (2024)

Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes
by: Kim, Yehna, et al.
Published: (2025)

AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking
by: Kim, Vitaliy, et al.
Published: (2024)

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
by: Won, Soyoun, et al.
Published: (2023)

Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium
by: Nam, Woo-Jeoung, et al.
Published: (2022)

Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
by: Kong, Heejo, et al.
Published: (2025)

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

TIFu: Tri-directional Implicit Function for High-Fidelity 3D Character Reconstruction
by: Lim, Byoungsung, et al.
Published: (2024)

Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition
by: Jung, Gunho, et al.
Published: (2025)

Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning
by: Kim, Suneung, et al.
Published: (2024)

MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval
by: Park, Jeong-Woo, et al.
Published: (2025)

RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation
by: Park, Geon, et al.
Published: (2025)

Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
by: Jang, Hyeonseo, et al.
Published: (2026)

FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval
by: Park, Jeong-Woo, et al.
Published: (2025)

ID-EA: Identity-driven Text Enhancement and Adaptation with Textual Inversion for Personalized Text-to-Image Generation
by: Jin, Hyun-Jun, et al.
Published: (2025)

Locality-aware Concept Bottleneck Model
by: Jeon, Sujin, et al.
Published: (2025)

UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices
by: Yeom, Seul-Ki, et al.
Published: (2024)

PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
by: Lee, Jongseo, et al.
Published: (2025)

DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval
by: Park, Geon, et al.
Published: (2026)

Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector
by: Zhang, Xianren, et al.
Published: (2024)

Local Representative Token Guided Merging for Text-to-Image Generation
by: Lee, Min-Jeong, et al.
Published: (2025)

Spatial Information Bottleneck for Interpretable Visual Recognition
by: Shu, Kaixiang, et al.
Published: (2025)

Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation
by: Choi, Sun-Hyuk, et al.
Published: (2025)

Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification
by: Lee, Junhyeok, et al.
Published: (2026)

Language-Guided Invariance Probing of Vision-Language Models
by: Lee, Jae Joong
Published: (2025)

Vortex Feature Positioning: Bridging Tabular IIoT Data and Image-Based Deep Learning
by: Park, Jong-Ik, et al.
Published: (2023)

Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
by: Lee, Junhyeok, et al.
Published: (2025)

Leveraging Textual Compositional Reasoning for Robust Change Captioning
by: Park, Kyu Ri, et al.
Published: (2025)

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

FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation
by: Woo, Young Beom, et al.
Published: (2025)

Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability
by: Zhang, Jianyang, et al.
Published: (2025)

LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement
by: Siddiqua, Namrah, et al.
Published: (2025)

Towards Improved Cervical Cancer Screening: Vision Transformer-Based Classification and Interpretability
by: Nguyen, Khoa Tuan, et al.
Published: (2025)

Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
by: Kim, Donghoon, et al.
Published: (2025)

Unveiling the Visual Counting Bottleneck in Vision-Language Models
by: Pang, Xingzhou, et al.
Published: (2026)