Image de couverture de livre

Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Upadhyay, Richa, Phlypo, Ronald, Saini, Rajkumar, Liwicki, Marcus
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning
par: Upadhyay, Richa, et autres
Publié: (2025)

Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review
par: Upadhyay, Richa, et autres
Publié: (2021)

Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts
par: Chhipa, Prakash Chandra, et autres
Publié: (2024)

LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion
par: Chippa, Meenakshi Subhash, et autres
Publié: (2024)

Möbius Transform for Mitigating Perspective Distortions in Representation Learning
par: Chhipa, Prakash Chandra, et autres
Publié: (2024)

A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions
par: Pihlgren, Gustav Grund, et autres
Publié: (2023)

Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning
par: Lê, Hoàng-Ân, et autres
Publié: (2024)

Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets
par: Lê, Hoàng-Ân, et autres
Publié: (2024)

MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning
par: Zhao, Zixian, et autres
Publié: (2025)

Task-conditioned adaptation of visual features in multi-task policy learning
par: Marza, Pierre, et autres
Publié: (2024)

FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning
par: Li, He, et autres
Publié: (2025)

CER-HV: A Human-in-the-Loop Framework for Cleaning Datasets Applied to Arabic-Script HTR
par: Al-azzawi, Sana, et autres
Publié: (2026)

Cross-Language Learning within Arabic Script for Low-Resource HTR
par: Al-azzawi, Sana, et autres
Publié: (2026)

Forgetting of task-specific knowledge in model merging-based continual learning
par: Hess, Timm, et autres
Publié: (2025)

Rethinking HTG Evaluation: Bridging Generation and Recognition
par: Nikolaidou, Konstantina, et autres
Publié: (2024)

DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
par: Nikolaidou, Konstantina, et autres
Publié: (2024)

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
par: Tevet, Guy, et autres
Publié: (2024)

On the importance of cross-task features for class-incremental learning
par: Soutif--Cormerais, Albin, et autres
Publié: (2021)

Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks
par: Anthes, Daniel, et autres
Publié: (2023)

CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering
par: Jin, Qiangguo, et autres
Publié: (2025)

Low-Resolution Chest X-ray Classification via Knowledge Distillation and Multi-task Learning
par: Akhter, Yasmeena, et autres
Publié: (2024)

SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion
par: Nazir, Danish, et autres
Publié: (2022)

ProFound: A moderate-sized vision foundation model for multi-task prostate imaging
par: Wang, Yipei, et autres
Publié: (2026)

Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration
par: Ai, Hao, et autres
Publié: (2024)

POPCat: Propagation of particles for complex annotation tasks
par: Yang, Adam Srebrnjak, et autres
Publié: (2024)

A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
par: Woerner, Stefano, et autres
Publié: (2024)

Body Segmentation Using Multi-task Learning
par: Jug, Julijan, et autres
Publié: (2022)

Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology
par: Nahhas, Omar S. M. El, et autres
Publié: (2024)

DLM-VMTL:A Double Layer Mapper for heterogeneous data video Multi-task prompt learning
par: Bo, Zeyi, et autres
Publié: (2024)

Diffusion-based Visual Anagram as Multi-task Learning
par: Xu, Zhiyuan, et autres
Publié: (2024)

Multi-task Gaze Estimation Via Unidirectional Convolution
par: Cheng, Zhang, et autres
Publié: (2024)

Computer vision tasks for intelligent aerospace missions: An overview
par: Chen, Huilin, et autres
Publié: (2024)

Toward task-driven satellite image super-resolution
par: Ziaja, Maciej, et autres
Publié: (2025)

Multi-task Learning For Joint Action and Gesture Recognition
par: Spathis, Konstantinos, et autres
Publié: (2025)

AI-driven visual monitoring of industrial assembly tasks
par: Nardon, Mattia, et autres
Publié: (2025)

Overview of LifeCLEF Plant Identification task 2020
par: Goeau, Herve, et autres
Publié: (2025)

Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling
par: Al-azzawi, Sana, et autres
Publié: (2026)

DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning
par: Lopes, Ivan, et autres
Publié: (2022)

Detailed delineation of the fetal brain in diffusion MRI via multi-task learning
par: Karimi, Davood, et autres
Publié: (2024)

Utilizing dynamic sparsity on pretrained DETR
par: Sedghi, Reza, et autres
Publié: (2025)