Cover Image

Revisiting Neural Networks for Continual Learning: An Architectural Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Aojun, Feng, Tao, Yuan, Hangjie, Song, Xiaotian, Sun, Yanan
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
by: Lu, Aojun, et al.
Published: (2025)

Adapt before Continual Learning
by: Lu, Aojun, et al.
Published: (2025)

Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
by: Lu, Aojun, et al.
Published: (2026)

C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning
by: Li, Wei, et al.
Published: (2025)

Make Continual Learning Stronger via C-Flat
by: Bian, Ang, et al.
Published: (2024)

A Faster Path to Continual Learning
by: Li, Wei, et al.
Published: (2026)

Continual GUI Agents
by: Liu, Ziwei, et al.
Published: (2026)

Towards Accurate and Robust Architectures via Neural Architecture Search
by: Ou, Yuwei, et al.
Published: (2024)

Loss Functions for Predictor-based Neural Architecture Search
by: Ji, Han, et al.
Published: (2025)

NOAH: Learning Pairwise Object Category Attentions for Image Classification
by: Li, Chao, et al.
Published: (2024)

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
by: Feng, Tao, et al.
Published: (2025)

NODI: Out-Of-Distribution Detection with Noise from Diffusion
by: Zhou, Jingqiu, et al.
Published: (2024)

Revisiting Supervision for Continual Representation Learning
by: Marczak, Daniel, et al.
Published: (2023)

Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
by: Feifel, Patrick, et al.
Published: (2025)

Revisiting Long-Tailed Learning: Insights from an Architectural Perspective
by: Pan, Yuhan, et al.
Published: (2024)

Optimizing Convolutional Neural Network Architecture
by: Balderas, Luis, et al.
Published: (2023)

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
by: Zou, Jinping, et al.
Published: (2024)

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective
by: Zhang, Ziwei, et al.
Published: (2021)

A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
by: Liu, Yao, et al.
Published: (2023)

An Adaptive Tangent Feature Perspective of Neural Networks
by: LeJeune, Daniel, et al.
Published: (2023)

Towards Redundancy-Free Sub-networks in Continual Learning
by: Chen, Cheng, et al.
Published: (2023)

DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation
by: Wang, Maolin, et al.
Published: (2025)

Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge
by: Lu, Yao, et al.
Published: (2024)

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
by: Frati, Lapo, et al.
Published: (2025)

Similarity of Neural Architectures using Adversarial Attack Transferability
by: Hwang, Jaehui, et al.
Published: (2022)

Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks
by: Palit, Sanchar, et al.
Published: (2024)

Analytic Convolutional Layer: A Step to Analytic Neural Network
by: Cui, Jingmao, et al.
Published: (2024)

Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search
by: Yu, Sixing, et al.
Published: (2022)

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
by: Jin, Can, et al.
Published: (2023)

Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks
by: Feng, Yangqi, et al.
Published: (2025)

Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context Adaptation
by: Daniel, Rui, et al.
Published: (2025)

Towards Robust Neural Networks via Orthogonal Diversity
by: Fang, Kun, et al.
Published: (2020)

Deep Learning Meets OBIA: Tasks, Challenges, Strategies, and Perspectives
by: Ma, Lei, et al.
Published: (2024)

Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models
by: Gu, Jeffrey, et al.
Published: (2025)

MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks
by: Mecharbat, Lotfi Abdelkrim, et al.
Published: (2025)

HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning
by: Li, Jianfeng, et al.
Published: (2024)

Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking
by: Tang, Wen-Jia, et al.
Published: (2024)

Remembering Transformer for Continual Learning
by: Sun, Yuwei, et al.
Published: (2024)

Towards the Characterization of Representations Learned via Capsule-based Network Architectures
by: Tawalbeh, Saja, et al.
Published: (2023)

Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network
by: Hoya, Tetsuya, et al.
Published: (2025)