Guiding Yourself with Your Own Insights: Student-Driven Knowledge Distillation
We propose a knowledge distillation framework that employs a proxy teacher based on the student network and a Feature Fusion Block to improve knowledge transfer efficiency.
Jan 1, 2025
Efficient Implicit SDF and Color Reconstruction via Shared Feature Field
We propose a weight-sharing encoder-decoder framework that jointly optimizes the signed distance field (SDF) and color field.
Dec 1, 2024
Reinforcement Learning Based UAV Swarm Fission-Fusion Approach with Integrated Validation of Perception and Control
We propose an integrated system for swarm control and perception validation, along with a reinforcement learning-based sub-cluster adversarial algorithm.
Oct 1, 2024
DFFG: Fast Gradient Iteration for Data-free Quantization
We propose DFFG, a data-free quantization method based on fast gradient iteration, which leverages a momentum-based FGSM strategy to efficiently generate data for model quantization.
Nov 1, 2023