About

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

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Latest papers without code

Security Vulnerability Detection Using Deep Learning Natural Language Processing

6 May 2021

Detecting security vulnerabilities in software before they are exploited has been a challenging problem for decades.

TRANSFER LEARNING VULNERABILITY DETECTION

Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

6 May 2021

For many (minority) languages, the resources needed to train large models are not available.

TRANSFER LEARNING

Continual Learning on the Edge with TensorFlow Lite

5 May 2021

In addition, we expand the TensorFlow Lite library to include continual learning capabilities, by integrating a simple replay approach into the head of the current transfer learning model.

CONTINUAL LEARNING TRANSFER LEARNING

End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

5 May 2021

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings.

SPEAKER IDENTIFICATION TRANSFER LEARNING

Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation

5 May 2021

To avoid the costly annotation of training data for unseen domains, unsupervised domain adaptation (UDA) attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain.

SEMANTIC SEGMENTATION TRANSFER LEARNING UNSUPERVISED DOMAIN ADAPTATION

Motion-Augmented Self-Training for Video Recognition at Smaller Scale

4 May 2021

With the motion model we generate pseudo-labels for a large unlabeled video collection, which enables us to transfer knowledge by learning to predict these pseudo-labels with an appearance model.

ACTION RECOGNITION OPTICAL FLOW ESTIMATION TRANSFER LEARNING VIDEO RECOGNITION

Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge

4 May 2021

On the one hand, it is conceivable that knowledge from one task could be useful for solving a related problem.

TRANSFER LEARNING

One Model to Rule them All: Towards Zero-Shot Learning for Databases

3 May 2021

In this paper, we present our vision of so called zero-shot learning for databases which is a new learning approach for database components.

TRANSFER LEARNING ZERO-SHOT LEARNING

Prediction of clinical tremor severity using Rank Consistent Ordinal Regression

3 May 2021

The videos are coupled with clinician assessed TETRAS scores, which are used as ground truth labels to train the DNN.

TRANSFER LEARNING

Adapting CRISP-DM for Idea Mining: A Data Mining Process for Generating Ideas Using a Textual Dataset

2 May 2021

The benefits of using standard process models for data mining, such as the de facto and the most popular, Cross-Industry-Standard-Process model for Data Mining (CRISP-DM) are reduced cost and time.

TRANSFER LEARNING