Cover Image

Task Switching Without Forgetting via Proximal Decoupling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shamsolmoali, Pourya, Zareapoor, Masoumeh, Granger, Eric, Smith, William A. P., Lu, Yue
Format:	Preprint
Published:	2026
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

IntRec: Intent-based Retrieval with Contrastive Refinement
by: Shamsolmoali, Pourya, et al.
Published: (2026)

SeTformer is What You Need for Vision and Language
by: Shamsolmoali, Pourya, et al.
Published: (2024)

HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images
by: Shamsolmoali, Pourya, et al.
Published: (2026)

Fractional Correspondence Framework in Detection Transformer
by: Zareapoor, Masoumeh, et al.
Published: (2025)

Finding Structure in Continual Learning
by: Shamsolmoali, Pourya, et al.
Published: (2026)

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
by: Shamsolmoali, Pourya, et al.
Published: (2025)

Multi-Domain Learning with Global Expert Mapping
by: Shamsolmoali, Pourya, et al.
Published: (2026)

Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
by: Guichemerre, Alexis, et al.
Published: (2024)

Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification
by: Alehdaghi, Mahdi, et al.
Published: (2024)

From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification
by: Alehdaghi, Mahdi, et al.
Published: (2025)

Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification
by: Alehdaghi, Mahdi, et al.
Published: (2023)

TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel Conditioning
by: Mayet, Tsiry, et al.
Published: (2024)

Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI
by: Alehdaghi, Mahdi, et al.
Published: (2025)

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
by: Aminbeidokhti, Masih, et al.
Published: (2025)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
by: Li, He, et al.
Published: (2026)

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
by: Murtaza, Shakeeb, et al.
Published: (2024)

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
by: Murtaza, Shakeeb, et al.
Published: (2024)

Adaptation of Weakly Supervised Localization in Histopathology by Debiasing Predictions
by: Guichemerre, Alexis, et al.
Published: (2026)

Flower: A Flow-Matching Solver for Inverse Problems
by: Pourya, Mehrsa, et al.
Published: (2025)

Revisiting Mixout: An Overlooked Path to Robust Finetuning
by: Aminbeidokhti, Masih, et al.
Published: (2025)

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change
by: González-González, Manuela, et al.
Published: (2025)

TeD-Loc: Text Distillation for Weakly Supervised Object Localization
by: Murtaza, Shakeeb, et al.
Published: (2025)

Prompting Forgetting: Unlearning in GANs via Textual Guidance
by: Nagasubramaniam, Piyush, et al.
Published: (2025)

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
by: Belal, Atif, et al.
Published: (2024)

Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition
by: Belharbi, Soufiane, et al.
Published: (2024)

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
by: Aminbeidokhti, Masih, et al.
Published: (2025)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
by: Pan, Zecheng, et al.
Published: (2025)

Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
by: Zhong, Jincheng, et al.
Published: (2024)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
by: Deng, Kaiyuan, et al.
Published: (2026)

Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning
by: Liu, Shih-Wen, et al.
Published: (2026)

Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
by: Medeiros, Heitor Rapela, et al.
Published: (2024)

EXACFS -- A CIL Method to mitigate Catastrophic Forgetting
by: Balasubramanian, S, et al.
Published: (2024)

Domain Generalization by Rejecting Extreme Augmentations
by: Aminbeidokhti, Masih, et al.
Published: (2023)

Source-Free Domain Adaptation for YOLO Object Detection
by: Varailhon, Simon, et al.
Published: (2024)

Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling
by: Wei, Yipan, et al.
Published: (2025)

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
by: Wu, Junda, et al.
Published: (2025)

FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning
by: Lu, Yuxiang, et al.
Published: (2023)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
by: Deng, Kaiyuan, et al.
Published: (2026)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
by: Rezaei, Hossein, et al.
Published: (2024)

Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance
by: Moufad, Badr, et al.
Published: (2025)