Imagen de Portada

Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Yihang, Yu, Tianyuan, Bai, Liang, Guo, Yanming, Ruan, Yirun, Li, William, Zheng, Weishi
Formato:	Preprint
Publicado:	2025
Materias:	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

COLA: Context-aware Language-driven Test-time Adaptation
por: Zhang, Aiming, et al.
Publicado: (2025)

Multimodal Multilabel Classification by CLIP
por: Guo, Yanming
Publicado: (2024)

Anisotropic Diffusion Probabilistic Model for Imbalanced Image Classification
por: Kong, Jingyu, et al.
Publicado: (2024)

MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
por: Zhao, Xiran, et al.
Publicado: (2026)

Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement
por: Zhang, Dehuan, et al.
Publicado: (2023)

MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding
por: Li, Yu, et al.
Publicado: (2025)

MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance
por: Cao, Zihan, et al.
Publicado: (2025)

Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
por: Gu, Kai, et al.
Publicado: (2025)

Deep Learning for Visual Speech Analysis: A Survey
por: Sheng, Changchong, et al.
Publicado: (2022)

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
por: Tao, Yihang, et al.
Publicado: (2026)

FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting
por: Zhu, Huilin, et al.
Publicado: (2025)

Body Segmentation Using Multi-task Learning
por: Jug, Julijan, et al.
Publicado: (2022)

Bayesian Evidential Learning for Few-Shot Classification
por: Linghu, Xiongkun, et al.
Publicado: (2022)

FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection
por: Chen, Yulin, et al.
Publicado: (2025)

Co-Training Vision Language Models for Remote Sensing Multi-task Learning
por: Li, Qingyun, et al.
Publicado: (2025)

MAGE: A Multi-task Architecture for Gaze Estimation with an Efficient Calibration Module
por: Huang, Haoming, et al.
Publicado: (2025)

Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
por: Li, Jun, et al.
Publicado: (2026)

Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
por: Li, Jiahe, et al.
Publicado: (2026)

V2XCrafter: Learning to Generate Driving Scene Across Agents
por: Tao, Yihang, et al.
Publicado: (2026)

Diffusion-based Visual Anagram as Multi-task Learning
por: Xu, Zhiyuan, et al.
Publicado: (2024)

Multi-task Learning For Joint Action and Gesture Recognition
por: Spathis, Konstantinos, et al.
Publicado: (2025)

mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis
por: Liu, Quan, et al.
Publicado: (2024)

LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing
por: Xing, Weiwei, et al.
Publicado: (2025)

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization
por: Qi, Lei, et al.
Publicado: (2022)

Multi-Task Learning for Robot Perception with Imbalanced Data
por: Erkent, Ozgur
Publicado: (2026)

Revisiting Face Forgery Detection: From Facial Representation to Forgery Detection
por: Guo, Zonghui, et al.
Publicado: (2024)

OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
por: Wang, Yukun, et al.
Publicado: (2026)

On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy
por: Huang, Letian, et al.
Publicado: (2024)

PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence
por: Li, Zheng, et al.
Publicado: (2025)

Self-Supervised Multi-Scale Network for Blind Image Deblurring via Alternating Optimization
por: Guo, Lening, et al.
Publicado: (2024)

MAC-Lookup: Multi-Axis Conditional Lookup Model for Underwater Image Enhancement
por: Yi, Fanghai, et al.
Publicado: (2025)

AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
por: Yang, Enneng, et al.
Publicado: (2022)

AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection
por: Zhou, Jingchun, et al.
Publicado: (2023)

HSFusion: A high-level vision task-driven infrared and visible image fusion network via semantic and geometric domain transformation
por: Jiang, Chengjie, et al.
Publicado: (2024)

CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis
por: Han, Kai, et al.
Publicado: (2025)

Toward Safe, Trustworthy and Realistic Augmented Reality User Experience
por: Xiu, Yanming
Publicado: (2025)

SMILE: A Super-resolution Guided Multi-task Learning Method for Hyperspectral Unmixing
por: Li, Ruiying, et al.
Publicado: (2025)

Revisiting Multi-Task Visual Representation Learning
por: Di, Shangzhe, et al.
Publicado: (2026)

Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization
por: Li, Mengtian, et al.
Publicado: (2024)

Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
por: Jing, Zhang, et al.
Publicado: (2025)