Copertina

Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Yunpu, Zhang, Rui, Xiao, Junbin, Hou, Ruibo, Guo, Jiaming, Zhang, Zihao, Hao, Yifan, Chen, Yunji
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework
di: Zhao, Yunpu, et al.
Pubblicazione: (2024)

Decision-Driven Semantic Object Exploration for Legged Robots via Confidence-Calibrated Perception and Topological Subgoal Selection
di: Zhao, Guoyang, et al.
Pubblicazione: (2025)

EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration
di: Wu, Daiqing, et al.
Pubblicazione: (2025)

VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
di: Xiao, Wenyi, et al.
Pubblicazione: (2026)

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
di: Li, Haochen, et al.
Pubblicazione: (2024)

Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework
di: Jing, Hao, et al.
Pubblicazione: (2024)

World-Consistent Data Generation for Vision-and-Language Navigation
di: Zhong, Yu, et al.
Pubblicazione: (2024)

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
di: Xuan, Weihao, et al.
Pubblicazione: (2025)

Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models
di: Dang, Yunkai, et al.
Pubblicazione: (2026)

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
di: Zhang, Jialiang, et al.
Pubblicazione: (2026)

Assessing and Understanding Creativity in Large Language Models
di: Zhao, Yunpu, et al.
Pubblicazione: (2024)

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration
di: Zhang, Xiaoqing, et al.
Pubblicazione: (2024)

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
di: Guo, Jianing, et al.
Pubblicazione: (2025)

Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
di: Zhu, Younan, et al.
Pubblicazione: (2025)

Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors
di: Tao, Linwei, et al.
Pubblicazione: (2024)

On the Consistency of Video Large Language Models in Temporal Comprehension
di: Jung, Minjoon, et al.
Pubblicazione: (2024)

Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection
di: Liu, Xiangzhong, et al.
Pubblicazione: (2025)

Rethinking Practical and Efficient Quantization Calibration for Vision-Language Models
di: Shang, Zhenhao, et al.
Pubblicazione: (2026)

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
di: Chen, Junzhe, et al.
Pubblicazione: (2024)

Vision-Motion-Reference Alignment for Referring Multi-Object Tracking via Multi-Modal Large Language Models
di: Lv, Weiyi, et al.
Pubblicazione: (2025)

Confidence Self-Calibration for Multi-Label Class-Incremental Learning
di: Du, Kaile, et al.
Pubblicazione: (2024)

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
di: Li, Changyue, et al.
Pubblicazione: (2025)

A Prediction-as-Perception Framework for 3D Object Detection
di: Zhang, Song, et al.
Pubblicazione: (2026)

CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
di: Lin, Xiao, et al.
Pubblicazione: (2024)

Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds
di: Jing, Hao, et al.
Pubblicazione: (2025)

Calibrating Verbalized Confidence with Self-Generated Distractors
di: Wang, Victor, et al.
Pubblicazione: (2025)

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
di: Wu, Hao, et al.
Pubblicazione: (2026)

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
di: Xie, Chunlong, et al.
Pubblicazione: (2025)

DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation
di: Li, Wangkai, et al.
Pubblicazione: (2026)

Semantics-aware Motion Retargeting with Vision-Language Models
di: Zhang, Haodong, et al.
Pubblicazione: (2023)

Semantic Is Enough: Only Semantic Information For NeRF Reconstruction
di: Wang, Ruibo, et al.
Pubblicazione: (2024)

VORD: Visual Ordinal Calibration for Mitigating Object Hallucinations in Large Vision-Language Models
di: Neo, Dexter, et al.
Pubblicazione: (2024)

Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning
di: Li, Yang, et al.
Pubblicazione: (2026)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
di: Fang, Hao, et al.
Pubblicazione: (2024)

VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
di: Ye, Muchao, et al.
Pubblicazione: (2024)

Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation
di: Liu, Jie, et al.
Pubblicazione: (2025)

UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
di: Liang, Jiachen, et al.
Pubblicazione: (2024)

Training-Free Semantic Multi-Object Tracking with Vision-Language Models
di: Bonat, Laurence, et al.
Pubblicazione: (2026)

Defending Deepfake via Texture Feature Perturbation
di: Zhang, Xiao, et al.
Pubblicazione: (2025)

Calibrated and Efficient Sampling-Free Confidence Estimation for LiDAR Scene Semantic Segmentation
di: Miandashti, Hanieh Shojaei, et al.
Pubblicazione: (2024)