Imagen de Portada

Learning What Helps: Task-Aligned Context Selection for Vision Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Jingyu, Konuk, Emir, Strand, Fredrik, Matsoukas, Christos, Smith, Kevin
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

APLA: A Simple Adaptation Method for Vision Transformers
por: Sorkhei, Moein, et al.
Publicado: (2025)

Random Token Fusion for Multi-View Medical Diagnosis
por: Guo, Jingyu, et al.
Publicado: (2024)

Efficient Self-Supervised Adaptation for Medical Image Analysis
por: Sorkhei, Moein, et al.
Publicado: (2025)

Learning from Offline Foundation Features with Tensor Augmentations
por: Konuk, Emir, et al.
Publicado: (2024)

k-NN as a Simple and Effective Estimator of Transferability
por: Sorkhei, Moein, et al.
Publicado: (2025)

Pretrained ViTs Yield Versatile Representations For Medical Images
por: Matsoukas, Christos, et al.
Publicado: (2023)

Controlling Vision-Language Models for Multi-Task Image Restoration
por: Luo, Ziwei, et al.
Publicado: (2023)

VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings
por: Scabini, Leonardo, et al.
Publicado: (2025)

GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task
por: Ding, Ning, et al.
Publicado: (2023)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
por: Chen, Zhe, et al.
Publicado: (2023)

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
por: Ren, Sucheng, et al.
Publicado: (2024)

HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks
por: Guo, Jingyu, et al.
Publicado: (2026)

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

HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks
por: Li, Xiaoyu, et al.
Publicado: (2026)

Is Visual in-Context Learning for Compositional Medical Tasks within Reach?
por: Reiß, Simon, et al.
Publicado: (2025)

Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
por: Zhang, Yuming, et al.
Publicado: (2024)

MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
por: Liu, Yuhang, et al.
Publicado: (2025)

HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models
por: Bai, Xiangyu, et al.
Publicado: (2026)

Rotation Equivariant Mamba for Vision Tasks
por: Zhao, Zhongchen, et al.
Publicado: (2026)

Vision-Language Models for Vision Tasks: A Survey
por: Zhang, Jingyi, et al.
Publicado: (2023)

Leverage Task Context for Object Affordance Ranking
por: Huang, Haojie, et al.
Publicado: (2024)

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations
por: Li, Yanshu
Publicado: (2025)

Multidimensional Task Learning: A Unified Tensor Framework for Computer Vision Tasks
por: Ichi, Alaa El, et al.
Publicado: (2026)

A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships
por: Pereira, Gracile Astlin, et al.
Publicado: (2024)

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
por: Yan, Ziang, et al.
Publicado: (2024)

TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
por: Chen, Hanning, et al.
Publicado: (2024)

Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling
por: Liu, Shipeng, et al.
Publicado: (2026)

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
por: Zhong, Hanwen, et al.
Publicado: (2025)

Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
por: Zang, Ying, et al.
Publicado: (2025)

Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffusers
por: Liu, An-Lun, et al.
Publicado: (2025)

MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
por: Su, Junhao, et al.
Publicado: (2025)

Learning A Low-Level Vision Generalist via Visual Task Prompt
por: Chen, Xiangyu, et al.
Publicado: (2024)

Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving
por: Zheng, Mi, et al.
Publicado: (2025)

Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networks
por: Jin, Yuhui, et al.
Publicado: (2025)

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
por: Liu, Chengxin, et al.
Publicado: (2026)

Aligning What EEG Can See: Structural Representations for Brain-Vision Matching
por: Tang, Jingyi, et al.
Publicado: (2026)

Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies
por: Sarkar, Ayushman, et al.
Publicado: (2025)

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
por: Miao, Daiye, et al.
Publicado: (2025)

Solving Vision Tasks with Simple Photoreceptors Instead of Cameras
por: Atanov, Andrei, et al.
Publicado: (2024)

Component Selection for Craft Assembly Tasks
por: Isume, Vitor Hideyo, et al.
Publicado: (2024)