SOTAVerified

Data-free Knowledge Distillation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 75 papers

TitleStatusHype
CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation—0
Completely Heterogeneous Federated Learning—0
Conditional Generative Data-free Knowledge Distillation—0
Dense Depth Distillation with Out-of-Distribution Simulated Images—0
Data-Free Distillation of Language Model by Text-to-Text Transfer—0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis—0
Data-Free Knowledge Transfer: A Survey—0
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts—0
DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier—0
DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning—0
Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification—0
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images—0
Dual Discriminator Adversarial Distillation for Data-free Model Compression—0
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation—0
Explicit and Implicit Knowledge Distillation via Unlabeled Data—0
Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification—0
FedD2S: Personalized Data-Free Federated Knowledge Distillation—0
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks—0
FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning—0
Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks—0
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation—0
Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks—0
Mind the Gap Between Synthetic and Real: Utilizing Transfer Learning to Probe the Boundaries of Stable Diffusion Generated Data—0
Mitigating Cross-client GANs-based Attack in Federated Learning—0
Show:102550
← PrevPage 2 of 3Next →
All datasetsQNLISQuAD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GOLD (T5-base)Accuracy91.7—Unverified
2ZeroGen (T5-base)Accuracy88.5—Unverified
3ProGen (T5-base)Accuracy85.9—Unverified
4Prompt2Model (T5-base)Accuracy62.2—Unverified
#ModelMetricClaimedVerifiedStatus
1GOLD (T5-base)Exact Match75.2—Unverified
2Prompt2Model (T5-base)Exact Match74.4—Unverified
3ZeroGen (T5-base)Exact Match69.4—Unverified
4ProGen (T5-base)Exact Match68.1—Unverified