Imagen de Portada

Reducing catastrophic forgetting of incremental learning in the absence of rehearsal memory with task-specific token

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choi, Young Jo, Yoo, Min Kyoon, Park, Yu Rang
Formato:	Preprint
Publicado:	2024
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

The impact of model size on catastrophic forgetting in Online Continual Learning
por: Lee, Eunhae
Publicado: (2024)

On the importance of cross-task features for class-incremental learning
por: Soutif--Cormerais, Albin, et al.
Publicado: (2021)

Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data
por: Kim, Shiwon, et al.
Publicado: (2026)

Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift
por: Guo, Liangxuan, et al.
Publicado: (2023)

Class incremental learning with probability dampening and cascaded gated classifier
por: Pomponi, Jary, et al.
Publicado: (2024)

Comparison of Autoencoders for tokenization of ASL datasets
por: Praun-Petrovic, Vouk, et al.
Publicado: (2025)

Divide and not forget: Ensemble of selectively trained experts in Continual Learning
por: Rypeść, Grzegorz, et al.
Publicado: (2024)

Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
por: Jo, Sangwoo, et al.
Publicado: (2026)

Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
por: Jo, Dae Ung, et al.
Publicado: (2024)

Teaching Metric Distance to Discrete Autoregressive Language Models
por: Chung, Jiwan, et al.
Publicado: (2025)

When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization
por: Ramanujan, Vivek, et al.
Publicado: (2024)

Rehearsal-free Federated Domain-incremental Learning
por: Sun, Rui, et al.
Publicado: (2024)

Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications
por: Lew, Hah Min, et al.
Publicado: (2024)

FairDD: Enhancing Fairness with domain-incremental learning in dermatological disease diagnosis
por: Luo, Yiqin, et al.
Publicado: (2024)

Recommendation of data-free class-incremental learning algorithms by simulating future data
por: Feillet, Eva, et al.
Publicado: (2024)

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs
por: Lappe, Alexander, et al.
Publicado: (2025)

Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
por: Pascual, Ruben, et al.
Publicado: (2025)

Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks
por: Anthes, Daniel, et al.
Publicado: (2023)

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
por: Chen, Boyuan, et al.
Publicado: (2024)

Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning
por: Upadhyay, Richa, et al.
Publicado: (2025)

Can multimodal representation learning by alignment preserve modality-specific information?
por: Thoreau, Romain, et al.
Publicado: (2025)

Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
por: Sadikine, Amine, et al.
Publicado: (2024)

Task-conditioned adaptation of visual features in multi-task policy learning
por: Marza, Pierre, et al.
Publicado: (2024)

Resolution Chromatography of Diffusion Models
por: Hwang, Juno, et al.
Publicado: (2023)

REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
por: He, Run, et al.
Publicado: (2024)

Domain-incremental White Blood Cell Classification with Privacy-aware Continual Learning
por: Kumari, Pratibha, et al.
Publicado: (2025)

Brain-inspired analogical mixture prototypes for few-shot class-incremental learning
por: Li, Wanyi, et al.
Publicado: (2025)

ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
por: Kim, Jaeyung, et al.
Publicado: (2026)

The Solution for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition
por: Pan, Sishun, et al.
Publicado: (2024)

Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment
por: Park, Yong-Hyun, et al.
Publicado: (2024)

Steering Guidance for Personalized Text-to-Image Diffusion Models
por: Park, Sunghyun, et al.
Publicado: (2025)

Machine learning approach to brain tumor detection and classification
por: Oh, Alice, et al.
Publicado: (2024)

LookupViT: Compressing visual information to a limited number of tokens
por: Koner, Rajat, et al.
Publicado: (2024)

Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
por: Rabadán, Miquel Martí i, et al.
Publicado: (2026)

FedPOD: the deployable units of training for federated learning
por: Kim, Daewoon, et al.
Publicado: (2025)

Multimodal Transformer With a Low-Computational-Cost Guarantee
por: Park, Sungjin, et al.
Publicado: (2024)

Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing
por: Hong, Inpyo, et al.
Publicado: (2024)

Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
por: Choi, Seokeon, et al.
Publicado: (2025)

SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding
por: Park, Juhyeon, et al.
Publicado: (2025)

OmniField: Conditioned Neural Fields for Robust Multimodal Spatiotemporal Learning
por: Valencia, Kevin, et al.
Publicado: (2025)