Imagen de Portada

Understanding Generalization through Decision Pattern Shift

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deng, Huiqi, Li, Yibo, Zhang, Quanshi, Zhang, Peng, Pei, Hongbin, Hu, Xia
Formato:	Preprint
Publicado:	2026
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

Towards Attributions of Input Variables in a Coalition
por: Zheng, Xinhao, et al.
Publicado: (2023)

Explaining Generalization Power of a DNN Using Interactive Concepts
por: Zhou, Huilin, et al.
Publicado: (2023)

Does a Neural Network Really Encode Symbolic Concepts?
por: Li, Mingjie, et al.
Publicado: (2023)

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
por: Li, Mingjie, et al.
Publicado: (2023)

Revisiting Generalization Power of a DNN in Terms of Symbolic Interactions
por: Cheng, Lei, et al.
Publicado: (2025)

Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
por: Zhang, Junpeng, et al.
Publicado: (2024)

Neighborhood-Adaptive Generalized Linear Graph Embedding with Latent Pattern Mining
por: Peng, S., et al.
Publicado: (2025)

Technical Report: Quantifying and Analyzing the Generalization Power of a DNN
por: He, Yuxuan, et al.
Publicado: (2025)

Disentangling Regional Primitives for Image Generation
por: Chen, Zhengting, et al.
Publicado: (2024)

Defining and Extracting generalizable interaction primitives from DNNs
por: Chen, Lu, et al.
Publicado: (2024)

Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
por: Ren, Qihan, et al.
Publicado: (2023)

Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
por: Chen, Lu, et al.
Publicado: (2024)

Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
por: Zhang, Junpeng, et al.
Publicado: (2025)

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
por: Deng, Huiqi, et al.
Publicado: (2025)

Understanding Generalization in Diffusion Distillation via Probability Flow Distance
por: Zhang, Huijie, et al.
Publicado: (2025)

Towards the Resistance of Neural Network Watermarking to Fine-tuning
por: Tang, Ling, et al.
Publicado: (2025)

Layerwise Change of Knowledge in Neural Networks
por: Cheng, Xu, et al.
Publicado: (2024)

Control+Shift: Generating Controllable Distribution Shifts
por: Friedman, Roy, et al.
Publicado: (2024)

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
por: Peng, Yibo, et al.
Publicado: (2026)

Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary
por: Gomes, Inês, et al.
Publicado: (2024)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
por: Lou, Siyu, et al.
Publicado: (2024)

Towards the Dynamics of a DNN Learning Symbolic Interactions
por: Ren, Qihan, et al.
Publicado: (2024)

Adapting to Distribution Shift by Visual Domain Prompt Generation
por: Chi, Zhixiang, et al.
Publicado: (2024)

Robust Principal Component Analysis via Discriminant Sample Weight Learning
por: Deng, Yingzhuo, et al.
Publicado: (2024)

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
por: Li, Xiao, et al.
Publicado: (2025)

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
por: Zhang, Ruipeng, et al.
Publicado: (2024)

Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding
por: Zhang, Wenbo, et al.
Publicado: (2024)

Correcting Diffusion Generation through Resampling
por: Liu, Yujian, et al.
Publicado: (2023)

Generalized Evidential Deep Learning: From a Bayesian Perspective
por: Liu, Yuanye, et al.
Publicado: (2026)

Generative Autoencoding of Dropout Patterns
por: Maeda, Shunta
Publicado: (2023)

Understanding Image2Video Domain Shift in Food Segmentation: An Instance-level Analysis on Apples
por: Park, Keonvin, et al.
Publicado: (2026)

InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization
por: Li, Ronghui, et al.
Publicado: (2026)

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
por: Wu, Yecheng, et al.
Publicado: (2024)

LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention
por: Du, Zewen, et al.
Publicado: (2024)

LAPA: Log-Domain Prediction-Driven Dynamic Sparsity Accelerator for Transformer Model
por: Wang, Huizheng, et al.
Publicado: (2025)

DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion
por: Wang, Zixiao, et al.
Publicado: (2025)

Dynamic Base model Shift for Delta Compression
por: Huang, Chenyu, et al.
Publicado: (2025)

Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
por: Taparia, Aditya, et al.
Publicado: (2024)

Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift
por: Kethavath, Harshith, et al.
Publicado: (2026)

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