CLDec 13, 2022

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

arXiv:2212.06385v2232 citationsh-index: 36
AI Analysis

This provides a flexible toolkit for researchers and practitioners to efficiently reproduce or build pre-training models across modalities, but it is incremental as it builds on existing modular design trends.

The authors tackled the problem of implementing diverse pre-training models across text, vision, and audio modalities by developing TencentPretrain, a modular toolkit that unifies model components, and demonstrated it matches original implementations on benchmarks.

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes