Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Has it Trained Yet? A Workshop for Algorithmic Efficiency in Practical Neural Network Training

APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations

Elan Rosenfeld · Preetum Nakkiran · Hadi Pouransari · Oncel Tuzel · Fartash Faghri


Abstract:

Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets. In this work, we ask whether it is possible to achieve similar results with substantially less training time and data. We achieve this by taking advantage of existing pretrained unimodal encoders and careful curation of alignment data relevant to the downstream task of interest. We study a natural approach to aligning existing encoders via small auxiliary functions, and we find that this method is competitive with (or outperforms) state of the art in many settings while being less prone to overfitting, less costly to train, and more robust to distribution shift. With a carefully chosen alignment distribution, our method surpasses prior state of the art for ImageNet zero-shot classification on public data while using two orders of magnitude less time and data and training 77% fewer parameters.

Chat is not available.