Image de couverture de livre

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Zining, Wang, Weiqiu, Zhao, Zhicheng, Su, Fei, Men, Aidong, Meng, Hongying
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection
par: Chen, Zining, et autres
Publié: (2024)

Data-Efficient Generalization for Zero-shot Composed Image Retrieval
par: Chen, Zining, et autres
Publié: (2025)

Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
par: Xu, Yinsong, et autres
Publié: (2023)

MindShot: A Few-Shot Brain Decoding Framework via Transferring Cross-Subject Prior and Distilling Frequency Domain Knowledge
par: Jiang, Shuai, et autres
Publié: (2024)

TriDP-PTM: a three-stage distortion-perception tradeoff guides the pre-training model for radar cardiac sensing
par: Li, Jinye, et autres
Publié: (2026)

CIV-DG: Conditional Instrumental Variables for Domain Generalization in Medical Imaging
par: Bai, Shaojin, et autres
Publié: (2026)

COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models
par: Sinha, Sanchit, et autres
Publié: (2025)

Aligning What EEG Can See: Structural Representations for Brain-Vision Matching
par: Tang, Jingyi, et autres
Publié: (2026)

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
par: Vice, Jordan, et autres
Publié: (2025)

AdvST: Revisiting Data Augmentations for Single Domain Generalization
par: Zheng, Guangtao, et autres
Publié: (2023)

DG-DETR: Toward Domain Generalized Detection Transformer
par: Hwang, Seongmin, et autres
Publié: (2025)

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
par: Dong, Junhao, et autres
Publié: (2023)

PathGLS: Evaluating Pathology Vision-Language Models without Ground Truth through Multi-Dimensional Consistency
par: Chen, Minbing, et autres
Publié: (2026)

Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation
par: Li, Weize, et autres
Publié: (2024)

Hierarchical IoU Tracking based on Interval
par: Du, Yunhao, et autres
Publié: (2024)

YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions
par: Du, Yunhao, et autres
Publié: (2024)

Distilling Vision-Language Models on Millions of Videos
par: Zhao, Yue, et autres
Publié: (2024)

Sum-of-Checks: Structured Reasoning for Surgical Safety with Large Vision-Language Models
par: You, Weiqiu, et autres
Publié: (2026)

V2X-DG: Domain Generalization for Vehicle-to-Everything Cooperative Perception
par: Li, Baolu, et autres
Publié: (2025)

TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
par: Mu, Lianrui, et autres
Publié: (2023)

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding
par: Jiang, Jincen, et autres
Publié: (2024)

A Novel Cross-Perturbation for Single Domain Generalization
par: Zhao, Dongjia, et autres
Publié: (2023)

MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization
par: Yarici, Yavuz, et autres
Publié: (2026)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
par: Fang, Hao, et autres
Publié: (2024)

FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation
par: Deng, Zhipeng, et autres
Publié: (2025)

Dataset Distillation via Vision-Language Category Prototype
par: Zou, Yawen, et autres
Publié: (2025)

Visual-Advantage On-Policy Distillation for Vision-Language Models
par: Liu, Ruiqi, et autres
Publié: (2026)

VideoDistill: Language-aware Vision Distillation for Video Question Answering
par: Zou, Bo, et autres
Publié: (2024)

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
par: Umam, Ardian, et autres
Publié: (2023)

Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
par: Li, Yue, et autres
Publié: (2025)

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
par: Zhang, Tiezheng, et autres
Publié: (2025)

Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval
par: Li, Haiwen, et autres
Publié: (2024)

iKUN: Speak to Trackers without Retraining
par: Du, Yunhao, et autres
Publié: (2023)

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
par: Li, Zheng, et autres
Publié: (2024)

CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization
par: Kritikos, Antonios, et autres
Publié: (2026)

DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classification
par: Ren, Huantao, et autres
Publié: (2025)

TreeFedDG: Alleviating Global Drift in Federated Domain Generalization for Medical Image Segmentation
par: Song, Yucheng, et autres
Publié: (2025)

Adversarial Prompt Distillation for Vision-Language Models
par: Luo, Lin, et autres
Publié: (2024)

HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
par: Liang, Yihao, et autres
Publié: (2026)

WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation
par: Qian, Chenghao, et autres
Publié: (2024)