Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

by   Chao Jia, et al.

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) process. This costly curation process limits the size of datasets and hence hinders the scaling of trained models. In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme. Our visual representation achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations also set new state-of-the-art results on Flickr30K and MSCOCO benchmarks, even when compared with more sophisticated cross-attention models. The representations also enable cross-modality search with complex text and text + image queries.


page 2

page 3

page 8


Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

The availability of large-scale image captioning and visual question ans...

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Vision-Language Pre-training (VLP) has advanced the performance for many...

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

Large-scale vision and language representation learning has shown promis...

RedCaps: web-curated image-text data created by the people, for the people

Large datasets of paired images and text have become increasingly popula...

Improving Image Recognition by Retrieving from Web-Scale Image-Text Data

Retrieval augmented models are becoming increasingly popular for compute...

The Curious Robot: Learning Visual Representations via Physical Interactions

What is the right supervisory signal to train visual representations? Cu...

Probing Text Models for Common Ground with Visual Representations

Vision, as a central component of human perception, plays a fundamental ...

Please sign up or login with your details

Forgot password? Click here to reset