LaVin-DiT: Large Vision Diffusion Transformer

• URL: http://arxiv.org/abs/2411.11505v2
• Date: Sat, 23 Nov 2024 21:10:24 GMT
• Title: LaVin-DiT: Large Vision Diffusion Transformer
• Authors: Zhaoqing Wang, Xiaobo Xia, Runnan Chen, Dongdong Yu, Changhu Wang, Mingming Gong, Tongliang Liu,
• Abstract summary: LaVin-DiT is a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. We introduce key innovations to optimize generative performance for vision tasks. The model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks.
• Score: 99.98106406059333
• License:
• Abstract: This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational autoencoder that encodes data into a continuous latent space. Second, for generative modeling, we develop a joint diffusion transformer that progressively produces vision outputs. Third, for unified multi-task training, in-context learning is implemented. Input-target pairs serve as task context, which guides the diffusion transformer to align outputs with specific tasks within the latent space. During inference, a task-specific context set and test data as queries allow LaVin-DiT to generalize across tasks without fine-tuning. Trained on extensive vision datasets, the model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks. This work introduces a novel pathway for large vision foundation models, underscoring the promising potential of diffusion transformers. The code and models will be open-sourced.

Related papers

• Diffusion Models in 3D Vision: A Survey [11.116658321394755]
  We review the state-of-the-art approaches that leverage diffusion models for 3D visual tasks. These approaches include 3D object generation, shape completion, point cloud reconstruction, and scene understanding. We discuss potential solutions, including improving computational efficiency, enhancing multimodal fusion, and exploring the use of large-scale pretraining.
  arXiv  Detail & Related papers  (2024-10-07T04:12:23Z)
• ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer [40.32254040909614]
  We propose ACE, an All-round Creator and Editor, for visual generation tasks. We first introduce a unified condition format termed Long-context Condition Unit (LCU) We then propose a novel Transformer-based diffusion model that uses LCU as input, aiming for joint training across various generation and editing tasks.
  arXiv  Detail & Related papers  (2024-09-30T17:56:27Z)
• A Multitask Deep Learning Model for Classification and Regression of Hyperspectral Images: Application to the large-scale dataset [44.94304541427113]
  We propose a multitask deep learning model to perform multiple classification and regression tasks simultaneously on hyperspectral images. We validated our approach on a large hyperspectral dataset called TAIGA. A comprehensive qualitative and quantitative analysis of the results shows that the proposed method significantly outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-23T11:14:54Z)
• Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers [34.611309081801345]
  This paper focuses on enabling a single pre-trained diffusion transformer model to scale across multiple datasets swiftly. We propose DiffScaler, an efficient scaling strategy for diffusion models where we train a minimal amount of parameters to adapt to different tasks. We find that transformer-based diffusion models significantly outperform CNN-based diffusion models methods while performing fine-tuning over smaller datasets.
  arXiv  Detail & Related papers  (2024-04-15T17:55:43Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model [97.9548609175831]
  We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks. Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention. Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-08T09:08:40Z)
• ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias [76.16156833138038]
  We propose a novel Vision Transformer Advanced by Exploring intrinsic IB from convolutions, ie, ViTAE. ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context. In each transformer layer, ViTAE has a convolution block in parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network.
  arXiv  Detail & Related papers  (2021-06-07T05:31:06Z)
• Transformers in Vision: A Survey [101.07348618962111]
  Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence. Transformers require minimal inductive biases for their design and are naturally suited as set-functions. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline.
  arXiv  Detail & Related papers  (2021-01-04T18:57:24Z)

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.