Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models

• URL: http://arxiv.org/abs/2406.08487v3
• Date: Fri, 14 Jun 2024 00:52:35 GMT
• Title: Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
• Authors: Yi-Fan Zhang, Qingsong Wen, Chaoyou Fu, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin,
• Abstract summary: We propose a new framework, LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME) We extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. The proposed method achieves leading performance across various benchmarks with only 2 million training data.
• Score: 44.437693135170576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the most important tokens accounting for the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a `less is more' pattern, where \textit{utilizing fewer but more informative local image tokens leads to improved performance}. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data.

Related papers

• Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization [4.8454936010479335]
  We propose a Multi-view Pixel-wise Contrastive algorithm (MPC) for image forgery localization. Specifically, we first pre-train the backbone network with the supervised contrastive loss. Then the localization head is fine-tuned using the cross-entropy loss, resulting in a better pixel localizer.
  arXiv  Detail & Related papers  (2024-06-19T13:51:52Z)
• Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning [50.88504784466931]
  Multi-task dense prediction involves semantic segmentation, depth estimation, and surface normal estimation. Existing solutions typically rely on learning global image representations for global cross-task image matching. Our proposal involves modeling region-wise representations using Gaussian Distributions.
  arXiv  Detail & Related papers  (2024-03-15T12:41:30Z)
• Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval [11.696941841000985]
  Two-stage methods following retrieve-and-rerank paradigm have achieved excellent performance, but their separate local and global modules are inefficient to real-world applications. We propose a mechanism which attentively selects prominent local descriptors and infuse fine-grained semantic relations into the global representation. Our method achieves state-of-the-art single-stage image retrieval performance on benchmarks such as Revisited Oxford and Revisited Paris.
  arXiv  Detail & Related papers  (2023-08-08T03:06:10Z)
• Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
  This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network. We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
  arXiv  Detail & Related papers  (2022-04-19T17:59:45Z)
• Any-resolution Training for High-resolution Image Synthesis [55.19874755679901]
  Generative models operate at fixed resolution, even though natural images come in a variety of sizes. We argue that every pixel matters and create datasets with variable-size images, collected at their native resolutions. We introduce continuous-scale training, a process that samples patches at random scales to train a new generator with variable output resolutions.
  arXiv  Detail & Related papers  (2022-04-14T17:59:31Z)
• Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder [11.985083962982909]
  This paper proposes a novel image-specific solution, namely non-local variational autoencoder (textttNLVAE) textttNLVAE is introduced as a self-supervised strategy that reconstructs high-resolution images using disentangled information from the non-local neighbourhood. Experimental results from seven benchmark datasets demonstrate the effectiveness of the textttNLVAE model.
  arXiv  Detail & Related papers  (2022-04-02T18:43:55Z)
• DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features [42.62089148690047]
  We propose a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval. It attentively extracts representative local information with multi-atrous convolutions and self-attention at first. The whole framework is end-to-end differentiable and can be trained with image-level labels.
  arXiv  Detail & Related papers  (2021-08-06T03:14:09Z)
• InfinityGAN: Towards Infinite-Resolution Image Synthesis [92.40782797030977]
  We present InfinityGAN, a method to generate arbitrary-resolution images. We show how it trains and infers patch-by-patch seamlessly with low computational resources.
  arXiv  Detail & Related papers  (2021-04-08T17:59:30Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.