Imagen de Portada

Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Junpeng, Li, Qing, Lin, Liang, Zhang, Quanshi
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence 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

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

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

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

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

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

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

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

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

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

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
por: Lou, Siyu, 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)

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
por: Yaras, Can, et al.
Publicado: (2024)

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

Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
por: Baniecki, Hubert, et al.
Publicado: (2025)

Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
por: Yoshikawa, Yuya, et al.
Publicado: (2024)

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation
por: Havrylov, Volodymyr, et al.
Publicado: (2025)

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

Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning
por: Heidari, Marzi, et al.
Publicado: (2024)

Explaining Bayesian Neural Networks
por: Bykov, Kirill, et al.
Publicado: (2021)

Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
por: Han, Yunchu, et al.
Publicado: (2025)

Learning Visuotactile Skills with Two Multifingered Hands
por: Lin, Toru, et al.
Publicado: (2024)

Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
por: Furuta, Hiroki, et al.
Publicado: (2024)

SinBasis Networks: Matrix-Equivalent Feature Extraction for Wave-Like Optical Spectrograms
por: Zhu, Yuzhou, et al.
Publicado: (2025)

Point Cloud Understanding via Attention-Driven Contrastive Learning
por: Wang, Yi, et al.
Publicado: (2024)

Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data
por: Qiao, Yu, et al.
Publicado: (2024)

AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
por: Li, Yuhan, et al.
Publicado: (2024)

EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder
por: Mahmud, Hasanul, et al.
Publicado: (2024)

Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
por: Subhan, Ali, et al.
Publicado: (2026)

OMENN: One Matrix to Explain Neural Networks
por: Wróbel, Adam, et al.
Publicado: (2024)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy
por: Kawano, Keisuke, et al.
Publicado: (2024)

Token Activation Map to Visually Explain Multimodal LLMs
por: Li, Yi, et al.
Publicado: (2025)

Can Biases in ImageNet Models Explain Generalization?
por: Gavrikov, Paul, et al.
Publicado: (2024)

Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
por: Parchami-Araghi, Amin, et al.
Publicado: (2024)

Position: Do Not Explain Vision Models Without Context
por: Tomaszewska, Paulina, et al.
Publicado: (2024)

Explaining Model Overfitting in CNNs via GMM Clustering
por: Dou, Hui, et al.
Publicado: (2024)

TextCAM: Explaining Class Activation Map with Text
por: Zhao, Qiming, et al.
Publicado: (2025)

When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
por: Mu, Tongzhou, et al.
Publicado: (2024)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
por: Chen, Kun, et al.
Publicado: (2025)