ComNeck: Bridging Compressed Image Latents and Multimodal LLMs via Universal Transform-Neck

• URL: http://arxiv.org/abs/2407.19651v1
• Date: Mon, 29 Jul 2024 02:32:44 GMT
• Title: ComNeck: Bridging Compressed Image Latents and Multimodal LLMs via Universal Transform-Neck
• Authors: Chia-Hao Kao, Cheng Chien, Yu-Jen Tseng, Yi-Hsin Chen, Alessandro Gnutti, Shao-Yuan Lo, Wen-Hsiao Peng, Riccardo Leonardi,
• Abstract summary: This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs) We propose a novel framework with a lightweight transform-neck and a surrogate loss to adapt compressed image latents for MLLM-based vision tasks. Our framework has the striking feature excluding the downstream MLLMs from training the transform-neck, and potentially the neural image as well.
• Score: 45.83457913639876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to modalities (e.g. images) beyond text, but their billion scale hinders deployment on resource-constrained end devices. While cloud-hosted MLLMs could be available, transmitting raw, uncompressed images captured by end devices to the cloud requires an efficient image compression system. To address this, we focus on emerging neural image compression and propose a novel framework with a lightweight transform-neck and a surrogate loss to adapt compressed image latents for MLLM-based vision tasks. The proposed framework is generic and applicable to multiple application scenarios, where the neural image codec can be (1) pre-trained for human perception without updating, (2) fully updated for joint human and machine perception, or (3) fully updated for only machine perception. The transform-neck trained with the surrogate loss is universal, for it can serve various downstream vision tasks enabled by a variety of MLLMs that share the same visual encoder. Our framework has the striking feature of excluding the downstream MLLMs from training the transform-neck, and potentially the neural image codec as well. This stands out from most existing coding for machine approaches that involve downstream networks in training and thus could be impractical when the networks are MLLMs. Extensive experiments on different neural image codecs and various MLLM-based vision tasks show that our method achieves great rate-accuracy performance with much less complexity, demonstrating its effectiveness.

Related papers

• Large Language Models for Multimodal Deformable Image Registration [50.91473745610945]
  We propose a novel coarse-to-fine MDIR framework,LLM-Morph, for aligning the deep features from different modal medical images. Specifically, we first utilize a CNN encoder to extract deep visual features from cross-modal image pairs, then we use the first adapter to adjust these tokens, and use LoRA in pre-trained LLMs to fine-tune their weights. Third, for the alignment of tokens, we utilize other four adapters to transform the LLM-encoded tokens into multi-scale visual features, generating multi-scale deformation fields and facilitating the coarse-to-fine MDIR task
  arXiv  Detail & Related papers  (2024-08-20T09:58:30Z)
• A Single Transformer for Scalable Vision-Language Modeling [74.05173379908703]
  We present SOLO, a single transformer for visiOn-Language mOdeling. A unified single Transformer architecture, like SOLO, effectively addresses these scalability concerns in LVLMs. In this paper, we introduce the first open-source training recipe for developing SOLO, an open-source 7B LVLM.
  arXiv  Detail & Related papers  (2024-07-08T22:40:15Z)
• VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks [89.24440488456405]
  VisionLLM v2 is an end-to-end generalist multimodal large model (MLLM) It unifies visual perception, understanding, and generation within a single framework.
  arXiv  Detail & Related papers  (2024-06-12T16:44:50Z)
• Dense Connector for MLLMs [89.50595155217108]
  We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs. Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
  arXiv  Detail & Related papers  (2024-05-22T16:25:03Z)
• Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex [4.57590454144072]
  Recently, there has been a surge in the popularity of pre trained large language models (LLMs) This paper proposes a new multi-modal training paradigm, aligning with LLM, encoding fMRI activity in visual cortex.
  arXiv  Detail & Related papers  (2024-01-08T12:30:23Z)
• Frozen Transformers in Language Models Are Effective Visual Encoder Layers [26.759544759745648]
  Large language models (LLMs) are surprisingly strong encoders for purely visual tasks in the absence of language. Our work pushes the boundaries of leveraging LLMs for computer vision tasks. We propose the information filtering hypothesis to explain the effectiveness of pre-trained LLMs in visual encoding.
  arXiv  Detail & Related papers  (2023-10-19T17:59:05Z)
• 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)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)

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.