Classification Done Right for Vision-Language Pre-Training
This addresses the problem of efficient and effective vision-language pre-training for researchers and practitioners, offering a simpler alternative to contrastive methods like CLIP.
The paper tackles vision-language pre-training by introducing SuperClass, a classification method that uses tokenized raw text as labels without a text encoder, achieving superior performance on various downstream tasks compared to CLIP.
We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as supervised classification labels, without the need for additional text filtering or selection. Due to the absence of the text encoding as contrastive target, SuperClass does not require a text encoder and does not need to maintain a large batch size as CLIP does. SuperClass demonstrated superior performance on various downstream tasks, including classic computer vision benchmarks and vision language downstream tasks. We further explored the scaling behavior of SuperClass on model size, training length, or data size, and reported encouraging results and comparisons to CLIP. https://github.com/x-cls/superclass