From Unimodal to Multimodal: Scaling up Projectors to Align Modalities

• URL: http://arxiv.org/abs/2409.19425v1
• Date: Sat, 28 Sep 2024 17:57:32 GMT
• Title: From Unimodal to Multimodal: Scaling up Projectors to Align Modalities
• Authors: Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Noel E. O'Connor,
• Abstract summary: We propose a novel approach that aligns vision and language modalities using only projection layers on pretrained, frozen unimodal encoders. Our method exploits the high semantic similarity between embedding spaces of well-trained vision and language models. It involves selecting semantically similar encoders in the latent space, curating a concept-rich dataset of image-caption pairs, and training simple projectors.
• Score: 16.733970553781887
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications due to their aligned latent space. However, this practice has left powerful unimodal encoders for both vision and language underutilized in multimodal applications which raises a key question: Is there a plausible way to connect unimodal backbones for zero-shot vision-language tasks? To this end, we propose a novel approach that aligns vision and language modalities using only projection layers on pretrained, frozen unimodal encoders. Our method exploits the high semantic similarity between embedding spaces of well-trained vision and language models. It involves selecting semantically similar encoders in the latent space, curating a concept-rich dataset of image-caption pairs, and training simple MLP projectors. We evaluated our approach on 12 zero-shot classification datasets and 2 image-text retrieval datasets. Our best model, utilizing DINOv2 and All-Roberta-Large text encoder, achieves 76\(\%\) accuracy on ImageNet with a 20-fold reduction in data and 65 fold reduction in compute requirements. The proposed framework enhances the accessibility of model development while enabling flexible adaptation across diverse scenarios, offering an efficient approach to building multimodal models by utilizing existing unimodal architectures. Code and datasets will be released soon.

Related papers

• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities [4.269326314400742]
  We introduce the Inner-Adaptor Architecture for multimodal large language models (MLLMs) The architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets.
  arXiv  Detail & Related papers  (2024-08-23T08:10:13Z)
• Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants [65.47222691674074]
  Muffin framework employs pre-trained vision-language models to act as providers of visual signals. UniMM-Chat dataset explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions.
  arXiv  Detail & Related papers  (2023-10-01T12:35:18Z)
• DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention [55.2825684201129]
  DeepSpeed-VisualChat is designed to optimize Large Language Models (LLMs) by incorporating multi-modal capabilities. Our framework is notable for (1) its open-source support for multi-round and multi-image dialogues, (2) introducing an innovative multi-modal causal attention mechanism, and (3) utilizing data blending techniques on existing datasets to assure seamless interactions.
  arXiv  Detail & Related papers  (2023-09-25T17:53:29Z)
• ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities [71.15303690248021]
  We release ONE-PEACE, a highly model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. With the scaling-friendly architecture and pretraining tasks, ONE-PEACE has the potential to expand to unlimited modalities.
  arXiv  Detail & Related papers  (2023-05-18T17:59:06Z)
• MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning [23.45678557013005]
  We propose a jointly masked multimodal modeling method to learn fine-grained multimodal representations. Our method performs joint masking on image-text input and integrates both implicit and explicit targets for the masked signals to recover. Our model achieves state-of-the-art performance on various downstream vision-language tasks, including image-text retrieval, visual question answering, visual reasoning, and weakly-supervised visual grounding.
  arXiv  Detail & Related papers  (2022-10-09T06:31:15Z)
• Multimodal Knowledge Alignment with Reinforcement Learning [103.68816413817372]
  ESPER extends language-only zero-shot models to unseen multimodal tasks, like image and audio captioning. Our key novelty is to use reinforcement learning to align multimodal inputs to language model generations without direct supervision. Experiments demonstrate that ESPER outperforms baselines and prior work on a variety of zero-shot tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:12:17Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)

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.