Data-free Knowledge Distillation
25 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Data-free Knowledge Distillation
Most implemented papers
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay
In particular, we design a Variational Autoencoder (VAE) with a training objective that is customized to learn the synthetic data representations optimally.
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation.
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing
To tackle this challenge, we propose a framework termed collaborative data-free knowledge distillation via multi-level feature sharing (CDFKD-MFS), which consists of a multi-header student module, an asymmetric adversarial data-free KD module, and an attention-based aggregation module.
Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion
The key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round so that the local model can be regularized towards the global optima.
Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy
Besides, CuDFKD adapts the generation target dynamically according to the status of student model.
Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint
Therefore, we propose mSARC to assure the student network can imitate not only the logit output but also the spatial activation region of the teacher network in order to alleviate the influence of unwanted noises in diverse synthetic images on distillation learning.
Synthetic data generation method for data-free knowledge distillation in regression neural networks
Knowledge distillation is the technique of compressing a larger neural network, known as the teacher, into a smaller neural network, known as the student, while still trying to maintain the performance of the larger neural network as much as possible.
Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?
Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images.
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model.
Customizing Synthetic Data for Data-Free Student Learning
Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student learning.