知识蒸馏方法

CVPR2023

Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation

EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization

Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization

itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection

Masked Autoencoders Enable Efficient Knowledge Distillers

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

DaFKD: Domain-Aware Federated Knowledge Distillation

MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning

Multi-Level Logit Distillation

ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector

Accelerating Dataset Distillation via Model Augmentation

Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss

Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class

Distilling Neural Fields for Real-Time Articulated Shape Reconstruction

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

Class Attention Transfer Based Knowledge Distillation

Efficient RGB-T Tracking via Cross-Modality Distillation

StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition

Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation