Imagen de Portada

DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Zhengxu, Li, Jun, Wu, Zhijian
Formato:	Preprint
Publicado:	2026
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

Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models
por: Peng, Ying, et al.
Publicado: (2025)

AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
por: Li, Yuqi, et al.
Publicado: (2025)

Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
por: Yu, Yu-Chu, et al.
Publicado: (2024)

Visual-Advantage On-Policy Distillation for Vision-Language Models
por: Liu, Ruiqi, et al.
Publicado: (2026)

MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
por: Li, Yuqi, et al.
Publicado: (2025)

KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment
por: Shi, Zhengxu
Publicado: (2024)

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
por: Bousselham, Walid, et al.
Publicado: (2025)

DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection
por: Zhang, Zhourui, et al.
Publicado: (2024)

Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity
por: Shuai, Zitao, et al.
Publicado: (2024)

Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers
por: Alves, Paulo Luza, et al.
Publicado: (2024)

Lightweight Model Pre-training via Language Guided Knowledge Distillation
por: Li, Mingsheng, et al.
Publicado: (2024)

Vision-Language Dataset Distillation
por: Wu, Xindi, et al.
Publicado: (2023)

Distilling Vision-Language Models on Millions of Videos
por: Zhao, Yue, et al.
Publicado: (2024)

Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
por: Asfour, Alaa, et al.
Publicado: (2026)

Dataset Distillation via Vision-Language Category Prototype
por: Zou, Yawen, et al.
Publicado: (2025)

Adaptive Teaching with Shared Classifier for Knowledge Distillation
por: Jang, Jaeyeon, et al.
Publicado: (2024)

Shrinking the Teacher: An Adaptive Teaching Paradigm for Asymmetric EEG-Vision Alignment
por: Wu, Lukun, et al.
Publicado: (2025)

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
por: Zhang, Tiezheng, et al.
Publicado: (2025)

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
por: Li, Zheng, et al.
Publicado: (2024)

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
por: Lee, Byung-Kwan, et al.
Publicado: (2025)

MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation
por: Zhu, Junyou, et al.
Publicado: (2024)

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
por: Cao, Yiming, et al.
Publicado: (2025)

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
por: Wu, Yuanchen, et al.
Publicado: (2025)

SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model
por: Cao, Bin, et al.
Publicado: (2024)

Long Context Transfer from Language to Vision
por: Zhang, Peiyuan, et al.
Publicado: (2024)

Lightweight Vision Transformer with Bidirectional Interaction
por: Fan, Qihang, et al.
Publicado: (2023)

VPTracker: Global Vision-Language Tracking via Visual Prompt
por: Wang, Jingchao, et al.
Publicado: (2025)

SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces
por: Wu, Guande, et al.
Publicado: (2025)

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
por: Umam, Ardian, et al.
Publicado: (2023)

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
por: Li, Yuanbo, et al.
Publicado: (2026)

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
por: Zhu, Yuhan, et al.
Publicado: (2024)

Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
por: Lee, Hongsin, et al.
Publicado: (2025)

VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
por: Wang, Jie, et al.
Publicado: (2026)

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
por: Liu, Yuan, et al.
Publicado: (2025)

Online In-Context Distillation for Low-Resource Vision Language Models
por: Kang, Zhiqi, et al.
Publicado: (2025)

RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing
por: Zhou, Huiling, et al.
Publicado: (2024)

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
por: Dong, Shaoqi, et al.
Publicado: (2025)

TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation
por: Shen, Yehui, et al.
Publicado: (2024)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
por: Hu, Yushi, et al.
Publicado: (2023)

Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation
por: Zhang, Jinchang, et al.
Publicado: (2025)