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 1441–1450 of 10307 papers

Title	Date	Tasks	Status	Hype
Lipschitz Lifelong Reinforcement Learning	Jan 15, 2020	reinforcement-learningReinforcement Learning	CodeCode Available	1
PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning	Jan 14, 2020	Deep Reinforcement Learningreinforcement-learning	CodeCode Available	1
Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation	Jan 13, 2020	Recommendation SystemsTransfer Learning	CodeCode Available	1
LTP: A New Active Learning Strategy for CRF-Based Named Entity Recognition	Jan 8, 2020	Active Learningnamed-entity-recognition	CodeCode Available	1
Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning	Jan 6, 2020	General ClassificationTransfer Learning	CodeCode Available	1
TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images	Jan 6, 2020	Table DetectionTable Extraction	CodeCode Available	1
Stance Detection Benchmark: How Robust Is Your Stance Detection?	Jan 6, 2020	Fake News DetectionMulti-Task Learning	CodeCode Available	1
Source Model Selection for Deep Learning in the Time Series Domain	Jan 3, 2020	Model SelectionTime Series	CodeCode Available	1
Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks	Dec 31, 2019	Imitation LearningIncremental Learning	CodeCode Available	1
A Broader Study of Cross-Domain Few-Shot Learning	Dec 16, 2019	Cross-Domain Few-Shotcross-domain few-shot learning	CodeCode Available	1

Show:10 25 50

← PrevPage 145 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