Unifying Vision-Language Representation Space with Single-tower Transformer

• URL: http://arxiv.org/abs/2211.11153v1
• Date: Mon, 21 Nov 2022 02:34:21 GMT
• Title: Unifying Vision-Language Representation Space with Single-tower Transformer
• Authors: Jiho Jang, Chaerin Kong, Donghyeon Jeon, Seonhoon Kim, Nojun Kwak
• Abstract summary: We train a model to learn a unified vision-language representation space that encodes both modalities at once in a modality-agnostic manner. We discover intriguing properties that distinguish OneR from the previous works that learn modality-specific representation spaces.
• Score: 29.604520441315135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contrastive learning is a form of distance learning that aims to learn invariant features from two related representations. In this paper, we explore the bold hypothesis that an image and its caption can be simply regarded as two different views of the underlying mutual information, and train a model to learn a unified vision-language representation space that encodes both modalities at once in a modality-agnostic manner. We first identify difficulties in learning a generic one-tower model for vision-language pretraining (VLP), and propose OneR as a simple yet effective framework for our goal. We discover intriguing properties that distinguish OneR from the previous works that learn modality-specific representation spaces such as zero-shot object localization, text-guided visual reasoning and multi-modal retrieval, and present analyses to provide insights into this new form of multi-modal representation learning. Thorough evaluations demonstrate the potential of a unified modality-agnostic VLP framework.

Related papers

• Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference [24.58277380514406]
  Natural Language Inference (NLI) is a crucial task in natural language processing. We propose an innovative ScenaFuse adapter that simultaneously integrates large-scale pre-trained linguistic knowledge and relevant visual information. Our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks.
  arXiv  Detail & Related papers  (2024-05-21T01:19:52Z)
• One-Shot Open Affordance Learning with Foundation Models [54.15857111929812]
  We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category. We propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data.
  arXiv  Detail & Related papers  (2023-11-29T16:23:06Z)
• Semantically Consistent Multi-view Representation Learning [11.145085584637744]
  We propose a novel Semantically Consistent Multi-view Representation Learning (SCMRL) SCMRL excavates underlying multi-view semantic consensus information and utilize the information to guide the unified feature representation learning. Compared with several state-of-the-art algorithms, extensive experiments demonstrate its superiority.
  arXiv  Detail & Related papers  (2023-03-08T04:27:46Z)
• Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models [57.08925810659545]
  We conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models. Our empirical observations suggest that vision-and-language models are better at label prediction tasks. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models.
  arXiv  Detail & Related papers  (2022-12-01T05:00:18Z)
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification [84.05253637260743]
  We propose a new framework, named Semantic-guided Visual Adapting (SgVA), to extend vision-language pre-trained models. SgVA produces discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
  arXiv  Detail & Related papers  (2022-11-28T14:58:15Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)
• Perceptual Grouping in Contrastive Vision-Language Models [59.1542019031645]
  We show how vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We propose a minimal set of modifications that results in models that uniquely learn both semantic and spatial information.
  arXiv  Detail & Related papers  (2022-10-18T17:01:35Z)
• An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
  Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
  arXiv  Detail & Related papers  (2022-05-16T11:23:42Z)

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.