MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

• URL: http://arxiv.org/abs/2410.10798v2
• Date: Tue, 15 Oct 2024 06:54:28 GMT
• Title: MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling
• Authors: Jian Yang, Dacheng Yin, Yizhou Zhou, Fengyun Rao, Wei Zhai, Yang Cao, Zheng-Jun Zha,
• Abstract summary: We propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss. We show that MMAR demonstrates much more superior performance than other joint multi-modal models.
• Score: 64.09238330331195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods inevitably suffer from loss of image information during understanding task, due to either image discretization or diffusion denoising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss. Differing from diffusion-based approaches, we disentangle the diffusion process from auto-regressive backbone model by employing a light-weight diffusion head on top each auto-regressed image patch embedding. In this way, when the model transits from image generation to understanding through text generation, the backbone model's hidden representation of the image is not limited to the last denoising step. To successfully train our method, we also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals. Through extensive evaluations on 18 image understanding benchmarks, MMAR demonstrates much more superior performance than other joint multi-modal models, matching the method that employs pretrained CLIP vision encoder, meanwhile being able to generate high quality images at the same time. We also showed that our method is scalable with larger data and model size.

Related papers

• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.06970466554273]
  We present Meissonic, which non-autoregressive masked image modeling (MIM) text-to-image elevates to a level comparable with state-of-the-art diffusion models like SDXL. We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Many-to-many Image Generation with Auto-regressive Diffusion Models [59.5041405824704]
  This paper introduces a domain-general framework for many-to-many image generation, capable of producing interrelated image series from a given set of images. We present MIS, a novel large-scale multi-image dataset, containing 12M synthetic multi-image samples, each with 25 interconnected images. We learn M2M, an autoregressive model for many-to-many generation, where each image is modeled within a diffusion framework.
  arXiv  Detail & Related papers  (2024-04-03T23:20:40Z)
• Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models [23.786473791344395]
  Cross-attention layers in diffusion models tend to disproportionately focus on certain tokens during the generation process. We introduce attention regulation, an on-the-fly optimization approach at inference time to align attention maps with the input text prompt. Experiment results show that our method consistently outperforms other baselines.
  arXiv  Detail & Related papers  (2024-03-11T02:18:27Z)
• Denoising Autoregressive Representation Learning [13.185567468951628]
  Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We show that the learned representation can be improved by using tailored noise schedules and longer training in larger models.
  arXiv  Detail & Related papers  (2024-03-08T10:19:00Z)
• TC-DiffRecon: Texture coordination MRI reconstruction method based on diffusion model and modified MF-UNet method [2.626378252978696]
  We propose a novel diffusion model-based MRI reconstruction method, named TC-DiffRecon, which does not rely on a specific acceleration factor for training. We also suggest the incorporation of the MF-UNet module, designed to enhance the quality of MRI images generated by the model.
  arXiv  Detail & Related papers  (2024-02-17T13:09:00Z)
• Image Inpainting via Tractable Steering of Diffusion Models [54.13818673257381]
  This paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs) We show that our approach can consistently improve the overall quality and semantic coherence of inpainted images with only 10% additional computational overhead.
  arXiv  Detail & Related papers  (2023-11-28T21:14:02Z)
• Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations [5.517338199249029]
  SR-DDPM is a class of generative models that produce high-quality images by reversing a noisy diffusion process. By exploiting the similarity between diverse data distributions, our method can scale to multiple tasks without compromising the image quality. We evaluate our method on standard image datasets and show that it outperforms both unconditional and conditional DDPM in terms of FID and SSIM metrics.
  arXiv  Detail & Related papers  (2023-11-27T22:30:26Z)
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion [144.9653045465908]
  We propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) Our approach yields promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2023-03-13T04:06:42Z)
• UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models [19.499490172426427]
  We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain.
  arXiv  Detail & Related papers  (2021-04-12T11:22:56Z)

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.