Abstract
Aligning the visual and language spaces requires to train deep neural networks from scratch on giant multimodal datasets; CLIP trains both an image and a text encoder, while LiT manages to train just the latter by taking advantage of a pretrained vision network. In this paper, we show that sparse relative representations are sufficient to align text and images without training any network. Our method relies on readily available single-domain encoders (trained with or without supervision) and a modest (in comparison) number of image-text pairs. ASIF redefines what constitutes a multimodal model by explicitly disentangling memory from processing: here the model is defined by the embedded pairs of all the entries in the multimodal dataset, in addition to the parameters of the two encoders. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multimodal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.
Abstract (translated)
URL
https://arxiv.org/abs/2210.01738
