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 )

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

Universal Language Model Fine-tuning for Text Classification

Content

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

High Quality Monocular Depth Estimation via Transfer Learning

ResNeSt: Split-Attention Networks

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Bag of Tricks for Image Classification with Convolutional Neural Networks

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Universal Sentence Encoder