Transferability
1개 벤치마크 · 논문 6편 · 이 태스크의 논문 보기 →
Benchmarks
classification benchmark
Most implemented
ETran: Energy-Based Transferability Estimation
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
Ranking Neural Checkpoints
Papers
ETran: Energy-Based Transferability Estimation
This paper addresses the problem of ranking pre-trained models for object detection and image classification. Selecting the best pre-trained model by fine-tuning is an expensive and time-consuming task. Previous works ha…
Classificationimage-classificationImage ClassificationObject+4Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each t…
AllTransferabilityPACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention. Although s…
Learning TheoryModel SelectionTransferabilityTransfer LearningLogME: Practical Assessment of Pre-trained Models for Transfer Learning
This paper studies task adaptive pre-trained model selection, an underexplored problem of assessing pre-trained models for the target task and select best ones from the model zoo \emph{without fine-tuning}. A few pilot w…
Model SelectionregressionTransferabilityTransfer LearningRanking Neural Checkpoints
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of ch…
TransferabilityTransfer LearningLEEP: A New Measure to Evaluate Transferability of Learned Representations
We introduce a new measure to evaluate the transferability of representations learned by classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy to compute: when given a classifier trai…
TransferabilityTransfer Learning