Copertina

GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Limarenko, Evgeny Alves, Studenikina, Anastasiia, Illarionova, Svetlana, Sharaev, Maxim
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BertsWin: Resolving Topological Sparsity in 3D Masked Autoencoders via Component-Balanced Structural Optimization
di: Limarenko, Evgeny Alves, et al.
Pubblicazione: (2025)

Biologically Inspired Deep Learning Approaches for Fetal Ultrasound Image Classification
di: Prochii, Rinat, et al.
Pubblicazione: (2025)

impuTMAE: Multi-modal Transformer with Masked Pre-training for Missing Modalities Imputation in Cancer Survival Prediction
di: Boyko, Maria, et al.
Pubblicazione: (2025)

Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective
di: Zhang, Zhi, et al.
Pubblicazione: (2024)

Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond
di: Kollias, Dimitrios, et al.
Pubblicazione: (2024)

Evaluating the Suitability of Different Intraoral Scan Resolutions for Deep Learning-Based Tooth Segmentation
di: Weekley, Daron, et al.
Pubblicazione: (2025)

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
di: Jeong, Wooseong, et al.
Pubblicazione: (2025)

Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation
di: Liu, Xuannan, et al.
Pubblicazione: (2024)

Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation
di: Tran, Minh-Tuan, et al.
Pubblicazione: (2024)

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
di: Yang, Longrong, et al.
Pubblicazione: (2024)

Resolving Task Objective Conflicts in Unified Model via Task-Aware Mixture-of-Experts
di: Zhang, Jiaxing, et al.
Pubblicazione: (2025)

EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting
di: Chen, Hao, et al.
Pubblicazione: (2026)

Gradient Similarity Surgery in Multi-Task Deep Learning
di: Borsani, Thomas, et al.
Pubblicazione: (2025)

Suppressing Gradient Conflict for Generalizable Deepfake Detection
di: Liu, Ming-Hui, et al.
Pubblicazione: (2025)

Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution
di: Lin, Shuchen, et al.
Pubblicazione: (2025)

LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
di: Fu, Fengyi, et al.
Pubblicazione: (2025)

Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator
di: Li, Jianze, et al.
Pubblicazione: (2024)

Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
di: Sun, Yi, et al.
Pubblicazione: (2023)

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

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals
di: Howard, Phillip, et al.
Pubblicazione: (2024)

Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution
di: Xu, Tianyi, et al.
Pubblicazione: (2024)

Integrating Radiomics with Deep Learning Enhances Multiple Sclerosis Lesion Delineation
di: Alsahanova, Nadezhda, et al.
Pubblicazione: (2025)

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
di: Gangwar, Neeraj, et al.
Pubblicazione: (2025)

Multi-Scale Implicit Transformer with Re-parameterize for Arbitrary-Scale Super-Resolution
di: Zhu, Jinchen, et al.
Pubblicazione: (2024)

Vision-based Conflict Detection within Crowds based on High-Resolution Human Pose Estimation for Smart and Safe Airport
di: Kheta, Karan, et al.
Pubblicazione: (2022)

Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance
di: Li, Wenjie, et al.
Pubblicazione: (2025)

Multimodal Fusion via Self-Consistent Task-Gradient Fields
di: Xiong, Jiayu, et al.
Pubblicazione: (2024)

Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images
di: Lu, Xiangyong, et al.
Pubblicazione: (2024)

Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
di: Chang, Chun-Peng, et al.
Pubblicazione: (2026)

HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
di: Kang, Yulei, et al.
Pubblicazione: (2026)

SGW-based Multi-Task Learning in Vision Tasks
di: Zhang, Ruiyuan, et al.
Pubblicazione: (2024)

CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection
di: Li, Yiheng, et al.
Pubblicazione: (2025)

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
di: Hadji, Isma, et al.
Pubblicazione: (2026)

Implicit Grid Convolution for Multi-Scale Image Super-Resolution
di: Lee, Dongheon, et al.
Pubblicazione: (2024)

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
di: Patel, Gaurav, et al.
Pubblicazione: (2025)

Guided Depth Map Super-Resolution via Multi-Scale Fusion U-shaped Mamba Network
di: Guo, Chenggang, et al.
Pubblicazione: (2025)

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration
di: Guo, Huijie, et al.
Pubblicazione: (2025)

SOMA-1M: A Large-Scale SAR-Optical Multi-resolution Alignment Dataset for Multi-Task Remote Sensing
di: Wu, Peihao, et al.
Pubblicazione: (2026)

High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
di: Jahedi, Azin, et al.
Pubblicazione: (2022)

Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
di: Wang, Haomin, et al.
Pubblicazione: (2026)