Transfer Learning

Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.

( Image credit: Subodh Malgonde )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1011–1020 of 10307 papers

Title	Date	Tasks	Status	Hype
PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python	Jun 17, 2021	BIG-bench Machine LearningDimensionality Reduction	CodeCode Available	1
An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis	Jun 17, 2021	Transfer Learning	CodeCode Available	1
Deep Subdomain Adaptation Network for Image Classification	Jun 17, 2021	ClassificationDomain Adaptation	CodeCode Available	1
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction	Jun 17, 2021	Event ExtractionTransfer Learning	CodeCode Available	1
Positional Contrastive Learning for Volumetric Medical Image Segmentation	Jun 16, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Learning Stable Classifiers by Transferring Unstable Features	Jun 15, 2021	Transfer Learning	CodeCode Available	1
rSoccer: A Framework for Studying Reinforcement Learning in Small and Very Small Size Robot Soccer	Jun 15, 2021	OpenAI Gymreinforcement-learning	CodeCode Available	1
Zero-shot Node Classification with Decomposed Graph Prototype Network	Jun 15, 2021	ClassificationNode Classification	CodeCode Available	1
Improving weakly supervised sound event detection with self-supervised auxiliary tasks	Jun 12, 2021	DecoderEvent Detection	CodeCode Available	1
HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML	Jun 11, 2021	Hyperparameter OptimizationTransfer Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 102 of 1031Next →

All datasets Office-Home 100 sleep nights of 8 caregivers BanglaLekha Isolated Dataset COCO70 KITTI Object Tracking Evaluation 2012 Retinal Fundus MultiDisease Image Dataset (RFMiD)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	APCLIP	Accuracy	84.2	—	Unverified
2	DFA-ENT	Accuracy	69.2	—	Unverified
3	DFA-SAFN	Accuracy	69.1	—	Unverified
4	EasyTL	Accuracy	63.3	—	Unverified
5	MEDA	Accuracy	60.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CNN	10-20% Mask PSNR	3.23	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Chatterjee, Dutta et al.[1]	Accuracy	96.12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Co-Tuning	Accuracy	85.65	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Physical Access	EER	5.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	riadd.aucmedi	AUROC	0.95	—	Unverified