Cover Image

Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yafei, Song, Shuaitian, Li, Huafeng, Wang, Shujuan, Liu, Yu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks
by: Yang, Zengyi, et al.
Published: (2024)

Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion
by: Yang, Zengyi, et al.
Published: (2026)

Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
by: Zhang, Yafei, et al.
Published: (2024)

MambaTrans: Multimodal Fusion Image Translation via Large Language Model Priors for Downstream Visual Tasks
by: Xu, Yushen, et al.
Published: (2025)

UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments
by: Su, Dayong, et al.
Published: (2025)

Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration
by: Yu, Xiaoyan, et al.
Published: (2024)

Understanding Cross Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation
by: Gong, Changqing, et al.
Published: (2025)

Infrared-Assisted Single-Stage Framework for Joint Restoration and Fusion of Visible and Infrared Images under Hazy Conditions
by: Li, Huafeng, et al.
Published: (2024)

Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared
by: Zhang, Yafei, et al.
Published: (2026)

RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks
by: Wang, Zhechao, et al.
Published: (2024)

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
by: Kowalczuk, Antoni, et al.
Published: (2024)

CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
by: Suharitdamrong, Wish, et al.
Published: (2026)

Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
by: Zhang, Yafei, et al.
Published: (2025)

TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks
by: Yu, Yang, et al.
Published: (2024)

CHITNet: A Complementary to Harmonious Information Transfer Network for Infrared and Visible Image Fusion
by: Du, Keying, et al.
Published: (2023)

CoA: Towards Real Image Dehazing via Compression-and-Adaptation
by: Ma, Long, et al.
Published: (2025)

What Sketch Explainability Really Means for Downstream Tasks
by: Bandyopadhyay, Hmrishav, et al.
Published: (2024)

Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement
by: Li, Pu, et al.
Published: (2026)

FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks
by: Zhang, Siqi, et al.
Published: (2025)

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
by: Li, Mingsong, et al.
Published: (2025)

Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization
by: Guo, Han, et al.
Published: (2024)

Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition
by: Cao, Congqi, et al.
Published: (2024)

Learned Image Compression for Earth Observation: Implications for Downstream Segmentation Tasks
by: Mollière, Christian, et al.
Published: (2025)

TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning
by: Baek, Seungmin, et al.
Published: (2025)

Dual-Granularity Cross-Modal Identity Association for Weakly-Supervised Text-to-Person Image Matching
by: Zhang, Yafei, et al.
Published: (2025)

Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks
by: Liang, Xiaoye, et al.
Published: (2025)

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

UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
by: Wang, Pu, et al.
Published: (2025)

Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
by: Dushenev, Daniil, et al.
Published: (2026)

DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer
by: Dong, Wei, et al.
Published: (2024)

ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks
by: Liu, Yang, et al.
Published: (2024)

Task-Aware Low-Rank Adaptation of Segment Anything Model
by: Wang, Xuehao, et al.
Published: (2024)

Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
by: Yang, Jin, et al.
Published: (2024)

ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
by: AlHindaassi, Fatmah, et al.
Published: (2025)

Balancing Task-invariant Interaction and Task-specific Adaptation for Unified Image Fusion
by: Hu, Xingyu, et al.
Published: (2025)

EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
by: Pei, Baoqi, et al.
Published: (2024)

How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
by: Sosa, Jose, et al.
Published: (2024)

Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
by: Wang, Ruiyi, et al.
Published: (2025)

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

Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding
by: Xie, Minghong, et al.
Published: (2024)