DreamLIP: Language-Image Pre-training with Long Captions

• URL: http://arxiv.org/abs/2403.17007v1
• Date: Mon, 25 Mar 2024 17:59:42 GMT
• Title: DreamLIP: Language-Image Pre-training with Long Captions
• Authors: Kecheng Zheng, Yifei Zhang, Wei Wu, Fan Lu, Shuailei Ma, Xin Jin, Wei Chen, Yujun Shen,
• Abstract summary: We re-caption 30M images with detailed descriptions using a pre-trained Multi-modality Large Language Model (MLLM) Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs. It is noteworthy that, on the tasks of image-text retrieval and semantic segmentation, our model trained with 30M image-text pairs achieves on par or even better performance than CLIP trained with 400M pairs.
• Score: 42.4063624671045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10 sentences), which are usually missing in existing datasets. Consequently, there are currently no clear evidences on whether and how language-image pre-training could benefit from long captions. To figure this out, we first re-caption 30M images with detailed descriptions using a pre-trained Multi-modality Large Language Model (MLLM), and then study the usage of the resulting captions under a contrastive learning framework. We observe that, each sentence within a long caption is very likely to describe the image partially (e.g., an object). Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs, and introduce a grouping loss to match the embeddings of each sub-caption with its corresponding local image patches in a self-supervised manner. Experimental results on a wide rage of downstream tasks demonstrate the consistent superiority of our method, termed DreamLIP, over previous alternatives, highlighting its fine-grained representational capacity. It is noteworthy that, on the tasks of image-text retrieval and semantic segmentation, our model trained with 30M image-text pairs achieves on par or even better performance than CLIP trained with 400M pairs. Project page is available at https://zyf0619sjtu.github.io/dream-lip.

Related papers

• LoTLIP: Improving Language-Image Pre-training for Long Text Understanding [71.04947115945349]
  We relabel the data with long captions, however, directly learning with which may lead to performance degradation in understanding short text. We then help the model catch up to its original level of short text understanding yet greatly enhance its capability of long text understanding. Our method demonstrates superior performance in long-text-image retrieval tasks.
  arXiv  Detail & Related papers  (2024-10-07T17:52:56Z)
• MLLMs-Augmented Visual-Language Representation Learning [70.5293060238008]
  We demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. We propose "text shearing" to maintain the quality and availability of extended captions.
  arXiv  Detail & Related papers  (2023-11-30T18:05:52Z)
• Contrastive Vision-Language Alignment Makes Efficient Instruction Learner [31.281236193979165]
  We study the task of extending the large language model (LLM) into a vision-language instruction-following model. Existing methods typically train a visual adapter to align the representation between a pre-trained vision transformer (ViT) and the LLM by a generative image captioning loss. We propose CG-VLM that applies Contrastive and Generative alignment objectives to effectively align the representation of ViT and LLM.
  arXiv  Detail & Related papers  (2023-11-29T03:29:46Z)
• COSA: Concatenated Sample Pretrained Vision-Language Foundation Model [78.32081709802873]
  Most vision-language foundation models employ image-text datasets for pretraining. We propose COSA, a COncatenated SAmple pretrained vision-language foundation model. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This transformation effectively converts existing image-text corpora into a pseudo long-form video-paragraph corpus.
  arXiv  Detail & Related papers  (2023-06-15T12:29:42Z)
• Text-based Person Search without Parallel Image-Text Data [52.63433741872629]
  Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are dominated by training models with parallel image-text pairs, which are very costly to collect. In this paper, we make the first attempt to explore TBPS without parallel image-text data.
  arXiv  Detail & Related papers  (2023-05-22T12:13:08Z)
• NewsStories: Illustrating articles with visual summaries [49.924916589209374]
  We introduce a large-scale multimodal dataset containing over 31M articles, 22M images and 1M videos. We show that state-of-the-art image-text alignment methods are not robust to longer narratives with multiple images. We introduce an intuitive baseline that outperforms these methods on zero-shot image-set retrieval by 10% on the GoodNews dataset.
  arXiv  Detail & Related papers  (2022-07-26T17:34:11Z)
• CapOnImage: Context-driven Dense-Captioning on Image [13.604173177437536]
  We introduce a new task called captioning on image (CapOnImage), which aims to generate dense captions at different locations of the image based on contextual information. We propose a multi-modal pre-training model with multi-level pre-training tasks that progressively learn the correspondence between texts and image locations. Compared with other image captioning model variants, our model achieves the best results in both captioning accuracy and diversity aspects.
  arXiv  Detail & Related papers  (2022-04-27T14:40:31Z)
• ClipCap: CLIP Prefix for Image Captioning [6.69087470775851]
  We use CLIP encoding as a prefix to the caption, by employing a simple mapping network, and then fine-tunes a language model to generate the image captions. We demonstrate our model achieves comparable results to state-of-the-art methods on the challenging Conceptual Captions and nocaps datasets.
  arXiv  Detail & Related papers  (2021-11-18T14:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.