SOTAVerified

Knowledge Distillation

Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1851–1900 of 4240 papers

TitleStatusHype
High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers—0
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws—0
Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillation—0
Hierarchical Selective Classification—0
Hierarchical Knowledge Distillation on Text Graph for Data-limited Attribute Inference—0
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?—0
Hierarchical Knowledge Distillation for Dialogue Sequence Labeling—0
Deep Collective Knowledge Distillation—0
A metric learning approach for endoscopic kidney stone identification—0
How to Backdoor the Knowledge Distillation—0
HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast—0
Heterogeneous Generative Knowledge Distillation with Masked Image Modeling—0
Heterogeneous Federated Learning Using Knowledge Codistillation—0
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning—0
Heterogeneous Continual Learning—0
Heterogeneous-Branch Collaborative Learning for Dialogue Generation—0
A method for estimating forest carbon storage distribution density via artificial intelligence generated content model—0
Adaptive Multiplane Image Generation from a Single Internet Picture—0
A Closer Look at Rehearsal-Free Continual Learning—0
Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning—0
HeteFedRec: Federated Recommender Systems with Model Heterogeneity—0
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment—0
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression—0
Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition—0
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers—0
Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation—0
HW-TSC’s Participation in the WMT 2020 News Translation Shared Task—0
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task—0
Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks—0
Decoupled Transformer for Scalable Inference in Open-domain Question Answering—0
Headache to Overstock? Promoting Long-tail Items through Debiased Product Bundling—0
Decoupled Transformer for Scalable Inference in Open-domain Question Answering—0
Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks—0
AMD: Automatic Multi-step Distillation of Large-scale Vision Models—0
hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation—0
Spectral Maps for Learning on Subgraphs—0
Harnessing Increased Client Participation with Cohort-Parallel Federated Learning—0
Harmonizing knowledge Transfer in Neural Network with Unified Distillation—0
HARD: Hard Augmentations for Robust Distillation—0
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation—0
I^2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding—0
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model—0
IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions—0
ICD-Face: Intra-class Compactness Distillation for Face Recognition—0
BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions—0
AMD: Adaptive Masked Distillation for Object Detection—0
HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training—0
If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval—0
Hands-on Guidance for Distilling Object Detectors—0
Decoupled Alignment for Robust Plug-and-Play Adaptation—0
Show:102550
← PrevPage 38 of 85Next →
All datasetsImageNetCIFAR-100COCO (Common Objects in Context)COCO 2017 valPASCAL VOCKITTI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43—Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53—Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93—Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8—Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6—Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9—Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7—Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55—Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5—Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86—Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76—Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6—Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28—Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08—Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93—Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68—Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5—Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68—Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP77.16—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP73.73—Unverified
3ADLIK-Faster (T: Faster R-CNN vit-base S: Faster R-CNN deit-small) box AP47.6—Unverified
4ADLIK-Mask (T: Mask R-CNN vit-base S: Mask R-CNN deit-small)mask AP42.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet50))AP@0.561.8—Unverified
2ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet18))AP@0.557.96—Unverified
3ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(mobilenet-v2))AP@0.555.18—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14—Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43—Unverified