Copertina

The Power of Certainty: How Confident Models Lead to Better Segmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Erol, Tugberk, Caglikantar, Tuba, Sarikaya, Duygu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision
di: Liao, Jiashu, et al.
Pubblicazione: (2025)

Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?
di: Wong, Xin Ci, et al.
Pubblicazione: (2025)

EmbedTalk: Triplane-Free Talking Head Synthesis using Embedding-Driven Gaussian Deformation
di: Saggar, Arpita, et al.
Pubblicazione: (2026)

Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping
di: Lonnqvist, Ben, et al.
Pubblicazione: (2023)

Certainty and Uncertainty Guided Active Domain Adaptation
di: Safaei, Bardia, et al.
Pubblicazione: (2025)

Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox
di: Kazakov, Allan, et al.
Pubblicazione: (2026)

Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation
di: Marschall, Samuel, et al.
Pubblicazione: (2024)

Seeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments
di: Xu, Yifan, et al.
Pubblicazione: (2025)

Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption
di: Erol, Mehmet Kaan
Pubblicazione: (2026)

Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation
di: Chen, Hang, et al.
Pubblicazione: (2025)

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
di: Jo, Sanghyun, et al.
Pubblicazione: (2025)

Adaptive Confidence-Wise Loss for Improved Lens Structure Segmentation in AS-OCT
di: Xiao, Zunjie, et al.
Pubblicazione: (2025)

Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty
di: Luo, Róisín, et al.
Pubblicazione: (2025)

3D Stylization via Large Reconstruction Model
di: Oztas, Ipek, et al.
Pubblicazione: (2025)

Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
di: Khan, Behraj, et al.
Pubblicazione: (2025)

UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets
di: Aditya, Arnav, et al.
Pubblicazione: (2025)

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
di: Jiang, Chenhan, et al.
Pubblicazione: (2026)

VFM-ISRefiner: Towards Better Adapting Vision Foundation Models for Interactive Segmentation of Remote Sensing Images
di: Wang, Deliang, et al.
Pubblicazione: (2025)

Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation
di: Gao, Junyu, et al.
Pubblicazione: (2024)

When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation
di: Liu, Pan, et al.
Pubblicazione: (2025)

Certainty-Validity: A Diagnostic Framework for Discrete Commitment Systems
di: Anderson, Datorien L.
Pubblicazione: (2026)

Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation
di: Borges, Bruno Laboissiere Camargos, et al.
Pubblicazione: (2024)

How Confident are Video Models? Empowering Video Models to Express their Uncertainty
di: Mei, Zhiting, et al.
Pubblicazione: (2025)

Defense That Attacks: How Robust Models Become Better Attackers
di: Awad, Mohamed, et al.
Pubblicazione: (2025)

From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification
di: Yuan, Xin, et al.
Pubblicazione: (2026)

Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation
di: Zenk, Maximilian, et al.
Pubblicazione: (2024)

Investigating Bias and Fairness in Appearance-based Gaze Estimation
di: Akgül, Burak, et al.
Pubblicazione: (2026)

Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective
di: Yao, Xing, et al.
Pubblicazione: (2025)

Better Call SAL: Towards Learning to Segment Anything in Lidar
di: Ošep, Aljoša, et al.
Pubblicazione: (2024)

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
di: Zhang, Shi-Chen, et al.
Pubblicazione: (2025)

Confidence Contours: Uncertainty-Aware Annotation for Medical Semantic Segmentation
di: Ye, Andre, et al.
Pubblicazione: (2023)

NeeCo: Image Synthesis of Novel Instrument States Based on Dynamic and Deformable 3D Gaussian Reconstruction
di: Zeng, Tianle, et al.
Pubblicazione: (2025)

Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
di: Liu, Jiazhen, et al.
Pubblicazione: (2025)

Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection
di: Guo, Yuelin, et al.
Pubblicazione: (2025)

Confident Learning for Object Detection under Model Constraints
di: Yu, Yingda, et al.
Pubblicazione: (2026)

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
di: Hamamci, Ibrahim Ethem, et al.
Pubblicazione: (2025)

How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model
di: Zhang, Yixin, et al.
Pubblicazione: (2023)

Unlocking the Power of SAM 2 for Few-Shot Segmentation
di: Xu, Qianxiong, et al.
Pubblicazione: (2025)

Unleashing the Power of Prompt-driven Nucleus Instance Segmentation
di: Shui, Zhongyi, et al.
Pubblicazione: (2023)

Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection
di: Zhang, Mingjin, et al.
Pubblicazione: (2024)