Browse SoTA > Methodology > Transfer Learning

Transfer Learning

567 papers with code · Methodology

Transfer learning is a methodology where weights from a model trained on one task are taken and either used (a) to construct a fixed feature extractor, (b) as weight initialization and/or fine-tuning.

( Image credit: Subodh Malgonde )

Benchmarks

Latest papers with code

AdaBoost-CNN: An adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning

Neurocomputing 2020 a-taherkhani/AdaBoost_CNN

AdaBoost-CNN is computationally efficient, as evidenced by the fact that the training simulation time of the proposed method is 47. 33 s, which is lower than the training simulation time required for a similar AdaBoost method without transfer learning, i. e. 225. 83 s on the imbalanced dataset.

TRANSFER LEARNING

0
03 Sep 2020

Fully Automated and Standardized Segmentation of Adipose Tissue Compartments by Deep Learning in Three-dimensional Whole-body MRI of Epidemiological Cohort Studies

5 Aug 2020lab-midas/med_segmentation

Methods: Quantification and localization of different adipose tissue compartments from whole-body MR images is of high interest to examine metabolic conditions.

TRANSFER LEARNING UNET SEGMENTATION

2
05 Aug 2020

Shape Adaptor: A Learnable Resizing Module

3 Aug 2020lorenmt/shape-adaptor

We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH TRANSFER LEARNING

13
03 Aug 2020

Force myography benchmark data for hand gesture recognition and transfer learning

29 Jul 2020exoskelebox/force-myography-hand-gesture-recognition-benchmark-data

This also illustrates that the dataset can serve as a benchmark dataset to facilitate research on transfer learning algorithms.

HAND GESTURE RECOGNITION HAND-GESTURE RECOGNITION TRANSFER LEARNING

1
29 Jul 2020

Generative Hierarchical Features from Synthesizing Images

20 Jul 2020genforce/ghfeat

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of observed data in an unsupervised manner.

FACE VERIFICATION IMAGE GENERATION TRANSFER LEARNING

23
20 Jul 2020

Do Adversarially Robust ImageNet Models Transfer Better?

16 Jul 2020MadryLab/robustness

Typically, better pre-trained models yield better transfer results, suggesting that initial accuracy is a key aspect of transfer learning performance.

TRANSFER LEARNING

324
16 Jul 2020

Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer

15 Jul 2020mikuhatsune/wsod_transfer

In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain.

TRANSFER LEARNING WEAKLY SUPERVISED OBJECT DETECTION

9
15 Jul 2020

Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration

14 Jul 2020JLiangLab/SemanticGenesis

To this end, we train deep models to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of the anatomy underneath medical images, resulting in a semantics-enriched, general-purpose, pre-trained 3D model, named Semantic Genesis.

REPRESENTATION LEARNING SELF-SUPERVISED LEARNING TRANSFER LEARNING

10
14 Jul 2020

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

12 Jul 2020andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning

In our experiments, we show that through alteration along different dimensions, the model learns to encode distinct aspects of speech.

SELF-SUPERVISED LEARNING SPEAKER RECOGNITION SPEECH RECOGNITION TRANSFER LEARNING

155
12 Jul 2020

Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning

10 Jul 2020maximecb/gym-miniworld

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills.

LANGUAGE MODELLING TRANSFER LEARNING WORD EMBEDDINGS

248
10 Jul 2020