Cover Image

Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Ying, Ye, Hongsen, Huang, Changxin, Hu, Xiping, Chen, Jian, Zeng, Runhao
Format:	Preprint
Published:	2025
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

Opening the Black Box: Preliminary Insights into Affective Modeling in Multimodal Foundation Models
by: Zhang, Zhen, et al.
Published: (2026)

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning
by: Zeng, Runhao, et al.
Published: (2024)

DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
by: He, Zhengxu, et al.
Published: (2026)

Towards Stable Cross-Domain Depression Recognition under Missing Modalities
by: Chen, Jiuyi, et al.
Published: (2025)

Temporal Action Detection Model Compression by Progressive Block Drop
by: Chen, Xiaoyong, et al.
Published: (2025)

AffectSeek: Agentic Affective Understanding in Long Videos under Vague User Queries
by: Zhang, Zhen, et al.
Published: (2026)

OVG-HQ: Online Video Grounding with Hybrid-modal Queries
by: Zeng, Runhao, et al.
Published: (2025)

Emotion Recognition from Skeleton Data: A Comprehensive Survey
by: Lu, Haifeng, et al.
Published: (2025)

Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models
by: Zhang, Jingrui, et al.
Published: (2026)

Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation
by: Zeng, Runhao, et al.
Published: (2025)

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
by: Deng, Qi, et al.
Published: (2024)

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

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

Adaptive Semantic Consistency for Cross-domain Few-shot Classification
by: Lu, Hengchu, et al.
Published: (2023)

Simultaneous 3D Object Segmentation and 6-DOF Pose Estimation
by: Liu, Hongsen
Published: (2019)

Towards Long Video Understanding via Fine-detailed Video Story Generation
by: You, Zeng, et al.
Published: (2024)

Object-Aware Video Matting with Cross-Frame Guidance
by: Zhang, Huayu, et al.
Published: (2025)

Color and Texture Dual Pipeline Lightweight Style Transfer
by: Jiang, ShiQi
Published: (2023)

Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
by: Zhang, Zhe, et al.
Published: (2026)

Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval
by: Li, Jiaxing, et al.
Published: (2025)

Single Trajectory Distillation for Accelerating Image and Video Style Transfer
by: Xu, Sijie, et al.
Published: (2024)

Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
by: Mansourian, Amir M., et al.
Published: (2025)

Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion
by: Liu, Runhao, et al.
Published: (2025)

Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation
by: George, Anjith, et al.
Published: (2026)

Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation
by: Zheng, Zhimeng, et al.
Published: (2024)

Multimodal Dataset Distillation via Phased Teacher Models
by: Guo, Shengbin, et al.
Published: (2026)

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
by: Du, Hongyang, et al.
Published: (2026)

Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures
by: Yang, Yaoxin, et al.
Published: (2025)

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
by: Chen, Tsai-Shien, et al.
Published: (2024)

Cross-Architecture Distillation Made Simple with Redundancy Suppression
by: Zhang, Weijia, et al.
Published: (2025)

Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation
by: Kurita, Teppei, et al.
Published: (2024)

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

Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing
by: Kong, Zhe, et al.
Published: (2024)

Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation
by: Wolf, Filip, et al.
Published: (2026)

Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model
by: Cuttano, Claudia, et al.
Published: (2024)

MT-Mark: Rethinking Image Watermarking via Mutual-Teacher Collaboration with Adaptive Feature Modulation
by: Ge, Fei, et al.
Published: (2025)

DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification
by: Sheng, Jiamu, et al.
Published: (2024)

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
by: Liang, Renjie, et al.
Published: (2023)

A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection
by: Wang, Yang, et al.
Published: (2023)

X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning
by: Shao, Maanping, et al.
Published: (2026)