Imagen de Portada

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Zirun, Jin, Tao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
por: Guo, Zirun, et al.
Publicado: (2025)

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
por: Guo, Zirun, et al.
Publicado: (2024)

LLM-I: LLMs are Naturally Interleaved Multimodal Creators
por: Guo, Zirun, et al.
Publicado: (2025)

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
por: Guo, Zirun, et al.
Publicado: (2024)

Efficient Prompting for Continual Adaptation to Missing Modalities
por: Guo, Zirun, et al.
Publicado: (2025)

Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation
por: He, Yongbo, et al.
Publicado: (2026)

Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
por: Guo, Zirun, et al.
Publicado: (2025)

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
por: Liang, Jian, et al.
Publicado: (2023)

UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation
por: Du, Chaoqun, et al.
Publicado: (2024)

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
por: Yu, Yongcan, et al.
Publicado: (2024)

Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
por: Zhang, Yunbei, et al.
Publicado: (2026)

Bridging Modalities via Progressive Re-alignment for Multimodal Test-Time Adaptation
por: Li, Jiacheng, et al.
Publicado: (2025)

Unraveling Batch Normalization for Realistic Test-Time Adaptation
por: Su, Zixian, et al.
Publicado: (2023)

Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation
por: Jang, Minguk, et al.
Publicado: (2024)

Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood
por: Nam, Gilhyun, et al.
Publicado: (2025)

Buffer layers for Test-Time Adaptation
por: Kim, Hyeongyu, et al.
Publicado: (2025)

Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
por: Guo, Zirun, et al.
Publicado: (2024)

Test-Time Adaptation for Depth Completion
por: Park, Hyoungseob, et al.
Publicado: (2024)

PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation
por: Maharana, Sarthak Kumar, et al.
Publicado: (2024)

Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
por: Su, Yongyi, et al.
Publicado: (2023)

Self-Bootstrapping for Versatile Test-Time Adaptation
por: Niu, Shuaicheng, et al.
Publicado: (2025)

Parameter-Selective Continual Test-Time Adaptation
por: Tian, Jiaxu, et al.
Publicado: (2024)

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
por: Su, Yongyi, et al.
Publicado: (2024)

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
por: Deng, Qi, et al.
Publicado: (2024)

Towards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution Shifts
por: Zhong, Guowei, et al.
Publicado: (2025)

Robustifying Diffusion-Denoised Smoothing Against Covariate Shift
por: Hedayatnia, Ali, et al.
Publicado: (2025)

Test Time Adaptation Using Adaptive Quantile Recalibration
por: Mehrbod, Paria, et al.
Publicado: (2025)

Ranked Entropy Minimization for Continual Test-Time Adaptation
por: Han, Jisu, et al.
Publicado: (2025)

ProtoTTA: Prototype-Guided Test-Time Adaptation
por: Abootorabi, Mohammad Mahdi, et al.
Publicado: (2026)

Mitigating the Bias in the Model for Continual Test-Time Adaptation
por: Chung, Inseop, et al.
Publicado: (2024)

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
por: Eyring, Luca, et al.
Publicado: (2025)

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
por: Hong, Minjie, et al.
Publicado: (2025)

MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm
por: Fan, Xiao, et al.
Publicado: (2025)

GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective
por: Wang, Xu, et al.
Publicado: (2026)

When Test-Time Adaptation Meets Self-Supervised Models
por: Han, Jisu, et al.
Publicado: (2025)

DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
por: Zhang, Yunbei, et al.
Publicado: (2024)

CLIPArTT: Adaptation of CLIP to New Domains at Test Time
por: Hakim, Gustavo Adolfo Vargas, et al.
Publicado: (2024)

Two Simple Principles for Diffusion-Based Test-Time Adaptation
por: Song, Kaiyu, et al.
Publicado: (2023)

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
por: Ma, Ke, et al.
Publicado: (2025)

NC-TTT: A Noise Contrastive Approach for Test-Time Training
por: Osowiechi, David, et al.
Publicado: (2024)