Cover Image

Forgetting of task-specific knowledge in model merging-based continual learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hess, Timm, van de Ven, Gido M, Tuytelaars, Tinne
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
by: Hess, Timm, et al.
Published: (2023)

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
by: Hess, Timm, et al.
Published: (2023)

Prediction Error-based Classification for Class-Incremental Learning
by: Zając, Michał, et al.
Published: (2023)

Continual Learning of Diffusion Models with Generative Distillation
by: Masip, Sergi, et al.
Published: (2023)

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
by: Dziadzio, Sebastian, et al.
Published: (2023)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
by: Goswami, Dipam, et al.
Published: (2026)

Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions
by: Jha, Abhishek, et al.
Published: (2024)

Continual Learning and Catastrophic Forgetting
by: van de Ven, Gido M., et al.
Published: (2024)

On the Computation of the Fisher Information in Continual Learning
by: van de Ven, Gido M.
Published: (2025)

Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation
by: Wu, Minye, et al.
Published: (2024)

Same accuracy, twice as fast: continuous training surpasses retraining from scratch
by: Verwimp, Eli, et al.
Published: (2025)

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
by: Swinnen, Jonathan, et al.
Published: (2026)

Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment
by: Behrad, Fatemeh, et al.
Published: (2025)

PEO: Training-Free Aesthetic Quality Enhancement in Pre-Trained Text-to-Image Diffusion Models with Prompt Embedding Optimization
by: Margaryan, Hovhannes, et al.
Published: (2025)

RGS-DR: Deferred Reflections and Residual Shading in 2D Gaussian Splatting
by: Kouros, Georgios, et al.
Published: (2025)

Object-Centric Pretraining via Target Encoder Bootstrapping
by: Đukić, Nikola, et al.
Published: (2025)

Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects
by: Kouros, Georgios, et al.
Published: (2025)

Visually-Aware Context Modeling for News Image Captioning
by: Qu, Tingyu, et al.
Published: (2023)

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks
by: Qu, Tingyu, et al.
Published: (2024)

Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
by: Mathioulakis, Fanis, et al.
Published: (2025)

Unsupervised Parameter Efficient Source-free Post-pretraining
by: Jha, Abhishek, et al.
Published: (2025)

DM-Align: Leveraging the Power of Natural Language Instructions to Make Changes to Images
by: Trusca, Maria Mihaela, et al.
Published: (2024)

Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Bias
by: Li, Mingxiao, et al.
Published: (2025)

Animate Your Motion: Turning Still Images into Dynamic Videos
by: Li, Mingxiao, et al.
Published: (2024)

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
by: Qu, Tingyu, et al.
Published: (2024)

Is this chart lying to me? Automating the detection of misleading visualizations
by: Tonglet, Jonathan, et al.
Published: (2025)

OASIS: Online Sample Selection for Continual Visual Instruction Tuning
by: Lee, Minjae, et al.
Published: (2025)

Unveiling the Ambiguity in Neural Inverse Rendering: A Parameter Compensation Analysis
by: Kouros, Georgios, et al.
Published: (2024)

BG-Triangle: Bézier Gaussian Triangle for 3D Vectorization and Rendering
by: Wu, Minye, et al.
Published: (2025)

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
by: Masip, Sergi, et al.
Published: (2026)

The Common Stability Mechanism behind most Self-Supervised Learning Approaches
by: Jha, Abhishek, et al.
Published: (2024)

On the Role of Individual Differences in Current Approaches to Computational Image Aesthetics
by: Chen, Li-Wei, et al.
Published: (2025)

A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
by: Stegmüller, Thomas, et al.
Published: (2024)

Self-Supervised Learning with a Multi-Task Latent Space Objective
by: De Plaen, Pierre-François, et al.
Published: (2026)

Contrastive Learning for Multi-Object Tracking with Transformers
by: De Plaen, Pierre-François, et al.
Published: (2023)

DAVE: Diagnostic benchmark for Audio Visual Evaluation
by: Radevski, Gorjan, et al.
Published: (2025)

Adversarial Dependence Minimization
by: De Plaen, Pierre-François, et al.
Published: (2025)

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
by: Wang, Zehao, et al.
Published: (2024)

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
by: Lebailly, Tim, et al.
Published: (2023)

Enhancing knowledge retention for continual learning with domain-specific adapters and features gating
by: Hedjazi, Mohamed Abbas, et al.
Published: (2025)