HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMs

• URL: http://arxiv.org/abs/2506.17608v1
• Date: Sat, 21 Jun 2025 06:13:56 GMT
• Title: HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMs
• Abstract summary: We develop an intuition for feature upsampling as a natural extension of high-resolution feature generation.<n>We demonstrate how a shallow feature enricher can achieve competitive results with tremendous reductions in training and inference time as well as computational cost.
• Score: 5.362066717455192
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since these features are obtained from large image encoders like ViT, they come with a significant increase in computational costs due to multiple calls to these encoders. In this work, we first develop an intuition for feature upsampling as a natural extension of high-resolution feature generation. Through extensive experiments and ablations, we demonstrate how a shallow feature enricher can achieve competitive results with tremendous reductions in training and inference time as well as computational cost, with upto 1.5x saving in FLOPs.

Related papers

• Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
  We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:28:07Z)
• MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval [111.99106496142474]
  Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure.<n>Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents.<n>We propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation.
  arXiv  Detail & Related papers  (2026-03-07T15:17:22Z)
• HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation [74.1872891313184]
  HRSeg is an efficient model with high-resolution fine-grained perception.<n>It features two key innovations: High-Resolution Perception (HRP) and High-Resolution Enhancement (HRE)
  arXiv  Detail & Related papers  (2025-07-17T08:09:31Z)
• JAFAR: Jack up Any Feature at Any Resolution [53.343826346140624]
  JAFAR is a lightweight and flexible feature upsampler for Foundation Visions.<n>It enhances the spatial resolution of visual features from any Foundation Vision to an arbitrary target resolution.<n>It generalizes remarkably well to significantly higher output scales.
  arXiv  Detail & Related papers  (2025-06-10T20:53:12Z)
• Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis [56.311477476580926]
  We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis.<n>LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space.
  arXiv  Detail & Related papers  (2025-05-31T07:28:32Z)
• Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention [54.42902794496325]
  Linear attention, a variant of softmax attention, demonstrates promise in global context modeling.<n>We propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution.<n>Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer.
  arXiv  Detail & Related papers  (2025-05-22T02:57:23Z)
• FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression [45.37530855889661]
  High-resolution images lead to a quadratic increase in the number of visual tokens input into Multi-modal Large Language Models. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.
  arXiv  Detail & Related papers  (2024-11-21T15:37:52Z)
• LinFusion: 1 GPU, 1 Minute, 16K Image [71.44735417472043]
  We introduce a low-rank approximation of a wide spectrum of popular linear token mixers. We find that the distilled model, termed LinFusion, achieves performance on par with or superior to the original SD. Experiments on SD-v1.5, SD-v2.1, and SD-XL demonstrate that LinFusion enables satisfactory and efficient zero-shot cross-resolution generation.
  arXiv  Detail & Related papers  (2024-09-03T17:54:39Z)
• UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks [36.61645124563195]
  We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions. We use semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images.
  arXiv  Detail & Related papers  (2024-07-02T11:02:19Z)
• MouSi: Poly-Visual-Expert Vision-Language Models [132.58949014605477]
  This paper proposes the use of ensemble experts technique to synergize the capabilities of individual visual encoders. This technique introduces a fusion network to unify the processing of outputs from different visual experts. In our implementation, this technique significantly reduces the positional occupancy in models like SAM, from a substantial 4096 to a more efficient and manageable 64 or even down to 1.
  arXiv  Detail & Related papers  (2024-01-30T18:09:11Z)
• Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution [11.256166497045792]
  We introduce a novel and efficient framework, the Mixture-of-Experts Implicit Super-Resolution (MoEISR)<n>MoEISR dynamically allocates the most suitable decoding expert to each pixel using a lightweight mapper module.<n>Our experiments demonstrate that MoEISR successfully reduces significant amount of floating point operations (FLOPs) while delivering comparable or superior peak signal-to-noise ratio (PSNR)
  arXiv  Detail & Related papers  (2023-11-20T05:34:36Z)
• ViR: Towards Efficient Vision Retention Backbones [97.93707844681893]
  We propose a new class of computer vision models, dubbed Vision Retention Networks (ViR) ViR has dual parallel and recurrent formulations, which strike an optimal balance between fast inference and parallel training with competitive performance. We have validated the effectiveness of ViR through extensive experiments with different dataset sizes and various image resolutions.
  arXiv  Detail & Related papers  (2023-10-30T16:55:50Z)
• Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting [44.51635913732913]
  This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Image matting is essentially a pixel-wise regression, and the ideal situation is to perceive the maximum opacity from the input image. We propose an Intensive Integration and Global Foreground Perception network (I2GFP) to integrate wider and higher feature streams.
  arXiv  Detail & Related papers  (2022-10-13T11:34:46Z)
• Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution [64.54162195322246]
  Convolutional neural network (CNN) has achieved great success on image super-resolution (SR) Most deep CNN-based SR models take massive computations to obtain high performance. We propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
  arXiv  Detail & Related papers  (2022-03-16T20:10:41Z)
• Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution [37.91175933401261]
  We present a unified formulation over widely-used multi-scale structures. We propose a generic and efficient multi-scale convolution unit -- Multi-Scale cross-Scale Share-weights convolution (MS$3$-Conv)
  arXiv  Detail & Related papers  (2020-08-01T10:44:06Z)

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.