Papers
arxiv:2401.09865

Improving fine-grained understanding in image-text pre-training

Published on Jan 18
· Submitted by akhaliq on Jan 19
Authors:
,
,
,
,
,
,
,
,

Abstract

We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multiple image patches often correspond to single words, we propose to learn a grouping of image patches for every token in the caption. To achieve this, we use a sparse similarity metric between image patches and language tokens and compute for each token a language-grouped vision embedding as the weighted average of patches. The token and language-grouped vision embeddings are then contrasted through a fine-grained sequence-wise loss that only depends on individual samples and does not require other batch samples as negatives. This enables more detailed information to be learned in a computationally inexpensive manner. SPARC combines this fine-grained loss with a contrastive loss between global image and text embeddings to learn representations that simultaneously encode global and local information. We thoroughly evaluate our proposed method and show improved performance over competing approaches both on image-level tasks relying on coarse-grained information, e.g. classification, as well as region-level tasks relying on fine-grained information, e.g. retrieval, object detection, and segmentation. Moreover, SPARC improves model faithfulness and captioning in foundational vision-language models.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2401.09865 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2401.09865 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2401.09865 in a Space README.md to link it from this page.

Collections including this paper 8