Cover Image

PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Minjae, Hur, Sungwoo, Hwang, Soojin, Kim, Won Hwa
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects
by: Moon, Sungphill, et al.
Published: (2024)

MoGIC: Boosting Motion Generation via Intention Understanding and Visual Context
by: Shi, Junyu, et al.
Published: (2025)

FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentation
by: Lee, Chang Won, et al.
Published: (2024)

Context-Based Visual-Language Place Recognition
by: Woo, Soojin, et al.
Published: (2024)

Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture
by: Kim, Dong-Hee, et al.
Published: (2024)

Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks
by: Choi, Sehwan, et al.
Published: (2024)

CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection
by: Kim, Jisong, et al.
Published: (2024)

DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
by: Jang, Soojin, et al.
Published: (2024)

Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
by: Jun, Jinyoung, et al.
Published: (2024)

Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
by: Jang, Hyeonseo, et al.
Published: (2026)

VideoMaMa: Mask-Guided Video Matting via Generative Prior
by: Lim, Sangbeom, et al.
Published: (2026)

ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
by: Kim, Beomyoung, et al.
Published: (2024)

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
by: Lin, Yuqi, et al.
Published: (2025)

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
by: Liu, Zhihua, et al.
Published: (2025)

Learning Multi-resolution Graph Edge Embedding for Discovering Brain Network Dysfunction in Neurological Disorders
by: Ma, Xin, et al.
Published: (2019)

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
by: Hur, Jiwan, et al.
Published: (2024)

GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation
by: Cai, Junhao, et al.
Published: (2024)

Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
by: Qi, Zhuang, et al.
Published: (2025)

GIC-DLC: Differentiable Logic Circuits for Hardware-Friendly Grayscale Image Compression
by: Aczel, Till, et al.
Published: (2026)

ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
by: Cao, Hao, et al.
Published: (2026)

Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation
by: Li, Yu-Jhe, et al.
Published: (2024)

MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation
by: Panboonyuen, Teerapong, et al.
Published: (2023)

Generalize Polyp Segmentation via Inpainting across Diverse Backgrounds and Pseudo-Mask Refinement
by: Ma, Jiajian, et al.
Published: (2024)

A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation
by: An, Seongkyu Choi Jhonghyun
Published: (2026)

Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
by: Wang, Zanyi, et al.
Published: (2025)

O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
by: Mur-Labadia, Lorenzo, et al.
Published: (2025)

MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
by: Ahn, Jihye, et al.
Published: (2024)

DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation
by: Cho, Suhwan, et al.
Published: (2025)

Iterative Prompt Refinement for Safer Text-to-Image Generation
by: Jeon, Jinwoo, et al.
Published: (2025)

SAMIC: Segment Anything with In-Context Spatial Prompt Engineering
by: Nagendra, Savinay, et al.
Published: (2024)

RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection
by: Kim, Jisong, et al.
Published: (2023)

MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation
by: Seong, Minjae, et al.
Published: (2024)

Explainable Continuous-Time Mask Refinement with Local Self-Similarity Priors for Medical Image Segmentation
by: Chatterjee, Rajdeep, et al.
Published: (2026)

Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
by: Kim, Chanyoung, et al.
Published: (2024)

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
by: Zhu, Beier, et al.
Published: (2023)

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation
by: Pak, Byeonghyun, et al.
Published: (2024)

EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything
by: Song, Joonhyeon, et al.
Published: (2024)

MaGGIe: Masked Guided Gradual Human Instance Matting
by: Huynh, Chuong, et al.
Published: (2024)

Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection
by: Salehi, Alireza, et al.
Published: (2025)

A Decoding Scheme with Successive Aggregation of Multi-Level Features for Light-Weight Semantic Segmentation
by: Yoo, Jiwon, et al.
Published: (2024)