Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment

• URL: http://arxiv.org/abs/2409.19425v2
• Date: Sun, 23 Mar 2025 14:00:30 GMT
• Title: Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment
• Authors: Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Noel E. O'Connor,
• Abstract summary: Recent findings suggest high semantic similarity between well-trained unimodal encoders.<n>We propose a novel framework that aligns vision and language using frozen unimodal encoders.
• 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. However, recent findings suggest high semantic similarity between well-trained unimodal encoders, which raises a key question: Is there a plausible way to connect unimodal backbones for vision-language tasks? To this end, we propose a novel framework that aligns vision and language using frozen unimodal encoders. 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 compared multi-modal alignment where models are trained from scratch. The proposed framework enhances the accessibility of multimodal model development while enabling flexible adaptation across diverse scenarios. Code and curated datasets are available at \texttt{github.com/mayug/freeze-align}.

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)
• OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities [0.08192907805418585]
  Cross-modal alignment learning integrates information from different modalities like text, image, audio and video to create unified models. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets. OneEncoder is a lightweight framework that progressively represents and aligns four modalities.
  arXiv  Detail & Related papers  (2024-09-17T10:38:46Z)
• 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)
• BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning [91.93547262073213]
  Vision-Language (VL) models with the Two-Tower architecture have dominated visual representation learning in recent years. We propose BridgeTower, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data.
  arXiv  Detail & Related papers  (2022-06-17T09:42:35Z)
• 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)
• Single-Stream Multi-Level Alignment for Vision-Language Pretraining [103.09776737512078]
  We propose a single stream model that aligns the modalities at multiple levels. We achieve this using two novel tasks: symmetric cross-modality reconstruction and a pseudo-labeled key word prediction. We demonstrate top performance on a set of Vision-Language downstream tasks such as zero-shot/fine-tuned image/text retrieval, referring expression, and VQA.
  arXiv  Detail & Related papers  (2022-03-27T21:16:10Z)
• 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)
• VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts [46.55920956687346]
  We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks. We propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs.
  arXiv  Detail & Related papers  (2021-11-03T17:20:36Z)
• A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation [131.33610549540043]
  We propose a novel graph-based multi-modal fusion encoder for NMT. We first represent the input sentence and image using a unified multi-modal graph. We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations.
  arXiv  Detail & Related papers  (2020-07-17T04:06:09Z)
• Contextual Encoder-Decoder Network for Visual Saliency Prediction [42.047816176307066]
  We propose an approach based on a convolutional neural network pre-trained on a large-scale image classification task. We combine the resulting representations with global scene information for accurately predicting visual saliency. Compared to state of the art approaches, the network is based on a lightweight image classification backbone.
  arXiv  Detail & Related papers  (2019-02-18T16:15:25Z)

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.