Copertina

Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ma, Yanbiao, Dai, Wei, Liu, Bowei, Chen, Jiayi, Huang, Wenke, Wan, Guancheng, Lu, Zhiwu, Yan, Junchi
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

Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
di: Ma, Yanbiao, et al.
Pubblicazione: (2025)

Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective
di: Ma, Yanbiao, et al.
Pubblicazione: (2025)

Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
di: Ma, Yanbiao, et al.
Pubblicazione: (2025)

Compositional Attribute Imbalance in Vision Datasets
di: Chen, Jiayi, et al.
Pubblicazione: (2025)

Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation
di: Chen, Siyu, et al.
Pubblicazione: (2025)

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
di: Xu, Hengbo, et al.
Pubblicazione: (2026)

Federated Graph Semantic and Structural Learning
di: Huang, Wenke, et al.
Pubblicazione: (2024)

FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
di: Tan, Zihan, et al.
Pubblicazione: (2024)

Geometric Prior-Guided Federated Prompt Calibration
di: Luo, Fei, et al.
Pubblicazione: (2025)

Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentation
di: Li, Xinhui, et al.
Pubblicazione: (2025)

Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity
di: Chen, Yuhang, et al.
Pubblicazione: (2024)

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models
di: Liang, Jian, et al.
Pubblicazione: (2025)

VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
di: Bi, Tianci, et al.
Pubblicazione: (2025)

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
di: Zhang, Guibin, et al.
Pubblicazione: (2025)

VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
di: Zhang, Yupeng, et al.
Pubblicazione: (2026)

S2FGL: Spatial Spectral Federated Graph Learning
di: Tan, Zihan, et al.
Pubblicazione: (2025)

Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach
di: Wang, Haoxuan, et al.
Pubblicazione: (2020)

VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors
di: Ming, Yuhang, et al.
Pubblicazione: (2026)

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation
di: Liang, Jian, et al.
Pubblicazione: (2025)

When would Vision-Proprioception Policies Fail in Robotic Manipulation?
di: Lu, Jingxian, et al.
Pubblicazione: (2026)

GMapLatent: Geometric Mapping in Latent Space
di: Zeng, Wei, et al.
Pubblicazione: (2025)

Privacy-Enhancing Paradigms within Federated Multi-Agent Systems
di: Shi, Zitong, et al.
Pubblicazione: (2025)

VFM-Loc: Zero-Shot Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies
di: Lu, Jun, et al.
Pubblicazione: (2026)

Cross Domain Policy Transfer with Effect Cycle-Consistency
di: Zhu, Ruiqi, et al.
Pubblicazione: (2024)

LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning
di: Xu, Haiying, et al.
Pubblicazione: (2026)

Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation
di: Zhao, Xingyue, et al.
Pubblicazione: (2025)

Latent Semantic Consensus For Deterministic Geometric Model Fitting
di: Xiao, Guobao, et al.
Pubblicazione: (2024)

Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space
di: Li, Yan, et al.
Pubblicazione: (2025)

The Automatic Calibration Method of the Compton Edge Based on Normalized Cross-correlation and Simulated Annealing Algorithm
di: Kong, Dehua, et al.
Pubblicazione: (2025)

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
di: Bi, Jinhe, et al.
Pubblicazione: (2025)

Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks
di: Jia, Yuang, et al.
Pubblicazione: (2025)

Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions
di: Xu, Wujiang, et al.
Pubblicazione: (2023)

Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation
di: Zhao, Jindong, et al.
Pubblicazione: (2026)

Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
di: Ma, Yanbiao, et al.
Pubblicazione: (2024)

VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation
di: Englert, Brunó B., et al.
Pubblicazione: (2025)

A Novel Control Method of Sugar Boiling Based on Model‐Free Adaptive Control and Neural Networks
di: Guancheng Lu, et al.
Pubblicazione: (2025)

No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
di: Wu, Cho-Ying, et al.
Pubblicazione: (2026)

Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
di: Huang, Wenke, et al.
Pubblicazione: (2024)

Cognitive Impairment in Maintenance Haemodialysis Patients: Early Identification and Management
di: Xingyun Wan, et al.
Pubblicazione: (2024)

Generative Human Motion Stylization in Latent Space
di: Guo, Chuan, et al.
Pubblicazione: (2024)