Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data

TL;DR

Neural Data Server (NDS) is a scalable search engine that efficiently recommends relevant large-scale datasets for transfer learning, improving model performance across various vision tasks.

Contribution

The paper introduces NDS, a compact mixture-of-experts model-based search engine that selects optimal pretraining data from large datasets for specific target domains.

Findings

Achieves state-of-the-art transfer learning performance

Demonstrates effectiveness across image classification, detection, segmentation

Low computational cost for data search

Abstract

Transfer learning has proven to be a successful technique to train deep learning models in the domains where little training data is available. The dominant approach is to pretrain a model on a large generic dataset such as ImageNet and finetune its weights on the target domain. However, in the new era of an ever-increasing number of massive datasets, selecting the relevant data for pretraining is a critical issue. We introduce Neural Data Server (NDS), a large-scale search engine for finding the most useful transfer learning data to the target domain. NDS consists of a dataserver which indexes several large popular image datasets, and aims to recommend data to a client, an end-user with a target application with its own small labeled dataset. The dataserver represents large datasets with a much more compact mixture-of-experts model, and employs it to perform data search in a series of dataserver-client transactions at a low computational cost. We show the effectiveness of NDS in various transfer learning scenarios, demonstrating state-of-the-art performance on several target datasets and tasks such as image classification, object detection and instance segmentation. Neural Data Server is available as a web-service at http://aidemos.cs.toronto.edu/nds/.