SOTAVerified

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

Showing 46614670 of 10307 papers

TitleStatusHype
Learning a Non-Linear Knowledge Transfer Model for Cross-View Action Recognition0
Learning Answer Embeddings for Visual Question Answering0
Learning ASR pathways: A sparse multilingual ASR model0
Learning Attentive Meta-Transfer0
Learning bilingual word embeddings with (almost) no bilingual data0
Learning Bound for Parameter Transfer Learning0
Associative embeddings for large-scale knowledge transfer with self-assessment0
Learning compact generalizable neural representations supporting perceptual grouping0
A transfer learning framework for weak-to-strong generalization0
A Statistical Theory of Regularization-Based Continual Learning0
Show:102550
← PrevPage 467 of 1031Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1APCLIPAccuracy84.2Unverified
2DFA-ENTAccuracy69.2Unverified
3DFA-SAFNAccuracy69.1Unverified
4EasyTLAccuracy63.3Unverified
5MEDAAccuracy60.3Unverified
#ModelMetricClaimedVerifiedStatus
1CNN10-20% Mask PSNR3.23Unverified
#ModelMetricClaimedVerifiedStatus
1Chatterjee, Dutta et al.[1]Accuracy96.12Unverified
#ModelMetricClaimedVerifiedStatus
1Co-TuningAccuracy85.65Unverified
#ModelMetricClaimedVerifiedStatus
1Physical AccessEER5.74Unverified
#ModelMetricClaimedVerifiedStatus
1riadd.aucmediAUROC0.95Unverified